Translating bus information into sign language for deaf people

This paper describes the application of language translation technologies for generating bus information in Spanish Sign Language (LSE: Lengua de Signos Española). In this work, two main systems have been developed: the first for translating text messages from information panels and the second for translating spoken Spanish into natural conversations at the information point of the bus company. Both systems are made up of a natural language translator (for converting a word sentence into a sequence of LSE signs), and a 3D avatar animation module (for playing back the signs). For the natural language translator, two technological approaches have been analyzed and integrated: an example-based strategy and a statistical translator. When translating spoken utterances, it is also necessary to incorporate a speech recognizer for decoding the spoken utterance into a word sequence, prior to the language translation module. This paper includes a detailed description of the field evaluation carried out in this domain. This evaluation has been carried out at the customer information office in Madrid involving both real bus company employees and deaf people. The evaluation includes objective measurements from the system and information from questionnaires. In the field evaluation, the whole translation presents an SER (Sign Error Rate) of less than 10% and a BLEU greater than 90%.

Dynamic topic-based adaptation of language models: a comparison between different approaches

This paper presents a dynamic LM adaptation based on the topic that has been identified on a speech segment. We use LSA and the given topic labels in the training dataset to obtain and use the topic models. We propose a dynamic language model adaptation to improve the recognition performance in "a two stages" AST system. The final stage makes use of the topic identification with two variants: the first on uses just the most probable topic and the other one depends on the relative distances of the topics that have been identified. We perform the adaptation of the LM as a linear interpolation between a background model and topic-based LM. The interpolation weight id dynamically adapted according to different parameters. The proposed method is evaluated on the Spanish partition of the EPPS speech database. We achieved a relative reduction in WER of 11.13% over the baseline system which uses a single blackground LM.

Extended phone log-likelihood ratio features and acoustic-based I-vectors for language recognition

This paper presents new techniques with relevant improvements added to the primary system presented by our group to the Albayzin 2012 LRE competition, where the use of any additional corpora for training or optimizing the models was forbidden. In this work, we present the incorporation of an additional phonotactic subsystem based on the use of phone log-likelihood ratio features (PLLR) extracted from different phonotactic recognizers that contributes to improve the accuracy of the system in a 21.4% in terms of Cavg (we also present results for the official metric during the evaluation, Fact). We will present how using these features at the phone state level provides significant improvements, when used together with dimensionality reduction techniques, especially PCA. We have also experimented with applying alternative SDC-like configurations on these PLLR features with additional improvements. Also, we will describe some modifications to the MFCC-based acoustic i-vector system which have also contributed to additional improvements. The final fused system outperformed the baseline in 27.4% in Cavg.

Language recognition using phonotactic-based shifted delta coefficients and multiple phone recognizers

A new language recognition technique based on the application of the philosophy of the Shifted Delta Coefficients (SDC) to phone log-likelihood ratio features (PLLR) is described. The new methodology allows the incorporation of long-span phonetic information at a frame-by-frame level while dealing with the temporal length of each phone unit. The proposed features are used to train an i-vector based system and tested on the Albayzin LRE 2012 dataset. The results show a relative improvement of 33.3% in Cavg in comparison with different state-of-the-art acoustic i-vector based systems. On the other hand, the integration of parallel phone ASR systems where each one is used to generate multiple PLLR coefficients which are stacked together and then projected into a reduced dimension are also presented. Finally, the paper shows how the incorporation of state information from the phone ASR contributes to provide additional improvements and how the fusion with the other acoustic and phonotactic systems provides an important improvement of 25.8% over the system presented during the competition.

GTH-UPM system for search on speech evaluation

This paper describes the GTH-UPM system for the Albayzin 2014 Search on Speech Evaluation. Teh evaluation task consists of searching a list of terms/queries in audio files. The GTH-UPM system we are presenting is based on a LVCSR (Large Vocabulary Continuous Speech Recognition) system. We have used MAVIR corpus and the Spanish partition of the EPPS (European Parliament Plenary Sessions) database for training both acoustic and language models. The main effort has been focused on lexicon preparation and text selection for the language model construction. The system makes use of different lexicon and language models depending on the task that is performed. For the best configuration of the system on the development set, we have obtained a FOM of 75.27 for the deyword spotting task.

Contributions to Speech Analytics based on Speech Recognition and Topic Identification

La última década ha sido testigo de importantes avances en el campo de la tecnología de reconocimiento de voz. Los sistemas comerciales existentes actualmente poseen la capacidad de reconocer habla continua de múltiples locutores, consiguiendo valores aceptables de error, y sin la necesidad de realizar procedimientos explícitos de adaptación. A pesar del buen momento que vive esta tecnología, el reconocimiento de voz dista de ser un problema resuelto. La mayoría de estos sistemas de reconocimiento se ajustan a dominios particulares y su eficacia depende de manera significativa, entre otros muchos aspectos, de la similitud que exista entre el modelo de lenguaje utilizado y la tarea específica para la cual se está empleando. Esta dependencia cobra aún más importancia en aquellos escenarios en los cuales las propiedades estadísticas del lenguaje varían a lo largo del tiempo, como por ejemplo, en dominios de aplicación que involucren habla espontánea y múltiples temáticas. En los últimos años se ha evidenciado un constante esfuerzo por mejorar los sistemas de reconocimiento para tales dominios. Esto se ha hecho, entre otros muchos enfoques, a través de técnicas automáticas de adaptación. Estas técnicas son aplicadas a sistemas ya existentes, dado que exportar el sistema a una nueva tarea o dominio puede requerir tiempo a la vez que resultar costoso. Las técnicas de adaptación requieren fuentes adicionales de información, y en este sentido, el lenguaje hablado puede aportar algunas de ellas. El habla no sólo transmite un mensaje, también transmite información acerca del contexto en el cual se desarrolla la comunicación hablada (e.g. acerca del tema sobre el cual se está hablando). Por tanto, cuando nos comunicamos a través del habla, es posible identificar los elementos del lenguaje que caracterizan el contexto, y al mismo tiempo, rastrear los cambios que ocurren en estos elementos a lo largo del tiempo. Esta información podría ser capturada y aprovechada por medio de técnicas de recuperación de información (information retrieval) y de aprendizaje de máquina (machine learning). Esto podría permitirnos, dentro del desarrollo de mejores sistemas automáticos de reconocimiento de voz, mejorar la adaptación de modelos del lenguaje a las condiciones del contexto, y por tanto, robustecer al sistema de reconocimiento en dominios con condiciones variables (tales como variaciones potenciales en el vocabulario, el estilo y la temática). En este sentido, la principal contribución de esta Tesis es la propuesta y evaluación de un marco de contextualización motivado por el análisis temático y basado en la adaptación dinámica y no supervisada de modelos de lenguaje para el robustecimiento de un sistema automático de reconocimiento de voz. Esta adaptación toma como base distintos enfoque de los sistemas mencionados (de recuperación de información y aprendizaje de máquina) mediante los cuales buscamos identificar las temáticas sobre las cuales se está hablando en una grabación de audio. Dicha identificación, por lo tanto, permite realizar una adaptación del modelo de lenguaje de acuerdo a las condiciones del contexto. El marco de contextualización propuesto se puede dividir en dos sistemas principales: un sistema de identificación de temática y un sistema de adaptación dinámica de modelos de lenguaje. Esta Tesis puede describirse en detalle desde la perspectiva de las contribuciones particulares realizadas en cada uno de los campos que componen el marco propuesto: _ En lo referente al sistema de identificación de temática, nos hemos enfocado en aportar mejoras a las técnicas de pre-procesamiento de documentos, asimismo en contribuir a la definición de criterios más robustos para la selección de index-terms. – La eficiencia de los sistemas basados tanto en técnicas de recuperación de información como en técnicas de aprendizaje de máquina, y específicamente de aquellos sistemas que particularizan en la tarea de identificación de temática, depende, en gran medida, de los mecanismos de preprocesamiento que se aplican a los documentos. Entre las múltiples operaciones que hacen parte de un esquema de preprocesamiento, la selección adecuada de los términos de indexado (index-terms) es crucial para establecer relaciones semánticas y conceptuales entre los términos y los documentos. Este proceso también puede verse afectado, o bien por una mala elección de stopwords, o bien por la falta de precisión en la definición de reglas de lematización. En este sentido, en este trabajo comparamos y evaluamos diferentes criterios para el preprocesamiento de los documentos, así como también distintas estrategias para la selección de los index-terms. Esto nos permite no sólo reducir el tamaño de la estructura de indexación, sino también mejorar el proceso de identificación de temática. – Uno de los aspectos más importantes en cuanto al rendimiento de los sistemas de identificación de temática es la asignación de diferentes pesos a los términos de acuerdo a su contribución al contenido del documento. En este trabajo evaluamos y proponemos enfoques alternativos a los esquemas tradicionales de ponderado de términos (tales como tf-idf ) que nos permitan mejorar la especificidad de los términos, así como también discriminar mejor las temáticas de los documentos. _ Respecto a la adaptación dinámica de modelos de lenguaje, hemos dividimos el proceso de contextualización en varios pasos. – Para la generación de modelos de lenguaje basados en temática, proponemos dos tipos de enfoques: un enfoque supervisado y un enfoque no supervisado. En el primero de ellos nos basamos en las etiquetas de temática que originalmente acompañan a los documentos del corpus que empleamos. A partir de estas, agrupamos los documentos que forman parte de la misma temática y generamos modelos de lenguaje a partir de dichos grupos. Sin embargo, uno de los objetivos que se persigue en esta Tesis es evaluar si el uso de estas etiquetas para la generación de modelos es óptimo en términos del rendimiento del reconocedor. Por esta razón, nosotros proponemos un segundo enfoque, un enfoque no supervisado, en el cual el objetivo es agrupar, automáticamente, los documentos en clusters temáticos, basándonos en la similaridad semántica existente entre los documentos. Por medio de enfoques de agrupamiento conseguimos mejorar la cohesión conceptual y semántica en cada uno de los clusters, lo que a su vez nos permitió refinar los modelos de lenguaje basados en temática y mejorar el rendimiento del sistema de reconocimiento. – Desarrollamos diversas estrategias para generar un modelo de lenguaje dependiente del contexto. Nuestro objetivo es que este modelo refleje el contexto semántico del habla, i.e. las temáticas más relevantes que se están discutiendo. Este modelo es generado por medio de la interpolación lineal entre aquellos modelos de lenguaje basados en temática que estén relacionados con las temáticas más relevantes. La estimación de los pesos de interpolación está basada principalmente en el resultado del proceso de identificación de temática. – Finalmente, proponemos una metodología para la adaptación dinámica de un modelo de lenguaje general. El proceso de adaptación tiene en cuenta no sólo al modelo dependiente del contexto sino también a la información entregada por el proceso de identificación de temática. El esquema usado para la adaptación es una interpolación lineal entre el modelo general y el modelo dependiente de contexto. Estudiamos también diferentes enfoques para determinar los pesos de interpolación entre ambos modelos. Una vez definida la base teórica de nuestro marco de contextualización, proponemos su aplicación dentro de un sistema automático de reconocimiento de voz. Para esto, nos enfocamos en dos aspectos: la contextualización de los modelos de lenguaje empleados por el sistema y la incorporación de información semántica en el proceso de adaptación basado en temática. En esta Tesis proponemos un marco experimental basado en una arquitectura de reconocimiento en ‘dos etapas’. En la primera etapa, empleamos sistemas basados en técnicas de recuperación de información y aprendizaje de máquina para identificar las temáticas sobre las cuales se habla en una transcripción de un segmento de audio. Esta transcripción es generada por el sistema de reconocimiento empleando un modelo de lenguaje general. De acuerdo con la relevancia de las temáticas que han sido identificadas, se lleva a cabo la adaptación dinámica del modelo de lenguaje. En la segunda etapa de la arquitectura de reconocimiento, usamos este modelo adaptado para realizar de nuevo el reconocimiento del segmento de audio. Para determinar los beneficios del marco de trabajo propuesto, llevamos a cabo la evaluación de cada uno de los sistemas principales previamente mencionados. Esta evaluación es realizada sobre discursos en el dominio de la política usando la base de datos EPPS (European Parliamentary Plenary Sessions - Sesiones Plenarias del Parlamento Europeo) del proyecto europeo TC-STAR. Analizamos distintas métricas acerca del rendimiento de los sistemas y evaluamos las mejoras propuestas con respecto a los sistemas de referencia. ABSTRACT The last decade has witnessed major advances in speech recognition technology. Today’s commercial systems are able to recognize continuous speech from numerous speakers, with acceptable levels of error and without the need for an explicit adaptation procedure. Despite this progress, speech recognition is far from being a solved problem. Most of these systems are adjusted to a particular domain and their efficacy depends significantly, among many other aspects, on the similarity between the language model used and the task that is being addressed. This dependence is even more important in scenarios where the statistical properties of the language fluctuates throughout the time, for example, in application domains involving spontaneous and multitopic speech. Over the last years there has been an increasing effort in enhancing the speech recognition systems for such domains. This has been done, among other approaches, by means of techniques of automatic adaptation. These techniques are applied to the existing systems, specially since exporting the system to a new task or domain may be both time-consuming and expensive. Adaptation techniques require additional sources of information, and the spoken language could provide some of them. It must be considered that speech not only conveys a message, it also provides information on the context in which the spoken communication takes place (e.g. on the subject on which it is being talked about). Therefore, when we communicate through speech, it could be feasible to identify the elements of the language that characterize the context, and at the same time, to track the changes that occur in those elements over time. This information can be extracted and exploited through techniques of information retrieval and machine learning. This allows us, within the development of more robust speech recognition systems, to enhance the adaptation of language models to the conditions of the context, thus strengthening the recognition system for domains under changing conditions (such as potential variations in vocabulary, style and topic). In this sense, the main contribution of this Thesis is the proposal and evaluation of a framework of topic-motivated contextualization based on the dynamic and non-supervised adaptation of language models for the enhancement of an automatic speech recognition system. This adaptation is based on an combined approach (from the perspective of both information retrieval and machine learning fields) whereby we identify the topics that are being discussed in an audio recording. The topic identification, therefore, enables the system to perform an adaptation of the language model according to the contextual conditions. The proposed framework can be divided in two major systems: a topic identification system and a dynamic language model adaptation system. This Thesis can be outlined from the perspective of the particular contributions made in each of the fields that composes the proposed framework: _ Regarding the topic identification system, we have focused on the enhancement of the document preprocessing techniques in addition to contributing in the definition of more robust criteria for the selection of index-terms. – Within both information retrieval and machine learning based approaches, the efficiency of topic identification systems, depends, to a large extent, on the mechanisms of preprocessing applied to the documents. Among the many operations that encloses the preprocessing procedures, an adequate selection of index-terms is critical to establish conceptual and semantic relationships between terms and documents. This process might also be weakened by a poor choice of stopwords or lack of precision in defining stemming rules. In this regard we compare and evaluate different criteria for preprocessing the documents, as well as for improving the selection of the index-terms. This allows us to not only reduce the size of the indexing structure but also to strengthen the topic identification process. – One of the most crucial aspects, in relation to the performance of topic identification systems, is to assign different weights to different terms depending on their contribution to the content of the document. In this sense we evaluate and propose alternative approaches to traditional weighting schemes (such as tf-idf ) that allow us to improve the specificity of terms, and to better identify the topics that are related to documents. _ Regarding the dynamic language model adaptation, we divide the contextualization process into different steps. – We propose supervised and unsupervised approaches for the generation of topic-based language models. The first of them is intended to generate topic-based language models by grouping the documents, in the training set, according to the original topic labels of the corpus. Nevertheless, a goal of this Thesis is to evaluate whether or not the use of these labels to generate language models is optimal in terms of recognition accuracy. For this reason, we propose a second approach, an unsupervised one, in which the objective is to group the data in the training set into automatic topic clusters based on the semantic similarity between the documents. By means of clustering approaches we expect to obtain a more cohesive association of the documents that are related by similar concepts, thus improving the coverage of the topic-based language models and enhancing the performance of the recognition system. – We develop various strategies in order to create a context-dependent language model. Our aim is that this model reflects the semantic context of the current utterance, i.e. the most relevant topics that are being discussed. This model is generated by means of a linear interpolation between the topic-based language models related to the most relevant topics. The estimation of the interpolation weights is based mainly on the outcome of the topic identification process. – Finally, we propose a methodology for the dynamic adaptation of a background language model. The adaptation process takes into account the context-dependent model as well as the information provided by the topic identification process. The scheme used for the adaptation is a linear interpolation between the background model and the context-dependent one. We also study different approaches to determine the interpolation weights used in this adaptation scheme. Once we defined the basis of our topic-motivated contextualization framework, we propose its application into an automatic speech recognition system. We focus on two aspects: the contextualization of the language models used by the system, and the incorporation of semantic-related information into a topic-based adaptation process. To achieve this, we propose an experimental framework based in ‘a two stages’ recognition architecture. In the first stage of the architecture, Information Retrieval and Machine Learning techniques are used to identify the topics in a transcription of an audio segment. This transcription is generated by the recognition system using a background language model. According to the confidence on the topics that have been identified, the dynamic language model adaptation is carried out. In the second stage of the recognition architecture, an adapted language model is used to re-decode the utterance. To test the benefits of the proposed framework, we carry out the evaluation of each of the major systems aforementioned. The evaluation is conducted on speeches of political domain using the EPPS (European Parliamentary Plenary Sessions) database from the European TC-STAR project. We analyse several performance metrics that allow us to compare the improvements of the proposed systems against the baseline ones.

A neural correlate of syntactic encoding during speech production

Spoken language is one of the most compact and structured ways to convey information. The linguistic ability to structure individual words into larger sentence units permits speakers to express a nearly unlimited range of meanings. This ability is rooted in speakers' knowledge of syntax and in the corresponding process of syntactic encoding. Syntactic encoding is highly automatized, operates largely outside of conscious awareness, and overlaps closely in time with several other processes of language production. With the use of positron emission tomography we investigated the cortical activations during spoken language production that are related to the syntactic encoding process. In the paradigm of restrictive scene description, utterances varying in complexity of syntactic encoding were elicited. Results provided evidence that the left Rolandic operculum, caudally adjacent to Broca's area, is involved in both sentence-level and local (phrase-level) syntactic encoding during speaking.

A new view of language acquisition

At the forefront of debates on language are new data demonstrating infants' early acquisition of information about their native language. The data show that infants perceptually “map” critical aspects of ambient language in the first year of life before they can speak. Statistical properties of speech are picked up through exposure to ambient language. Moreover, linguistic experience alters infants' perception of speech, warping perception in the service of language. Infants' strategies are unexpected and unpredicted by historical views. A new theoretical position has emerged, and six postulates of this position are described.

Preserved speech abilities and compensation following prefrontal damage.

Lesions to left frontal cortex in humans produce speech production impairments (nonfluent aphasia). These impairments vary from subject to subject and performance on certain speech production tasks can be relatively preserved in some patients. A possible explanation for preservation of function under these circumstances is that areas outside left prefrontal cortex are used to compensate for the injured brain area. We report here a direct demonstration of preserved language function in a stroke patient (LF1) apparently due to the activation of a compensatory brain pathway. We used functional brain imaging with positron emission tomography (PET) as a basis for this study.

Models of speech synthesis.

The term "speech synthesis" has been used for diverse technical approaches. In this paper, some of the approaches used to generate synthetic speech in a text-to-speech system are reviewed, and some of the basic motivations for choosing one method over another are discussed. It is important to keep in mind, however, that speech synthesis models are needed not just for speech generation but to help us understand how speech is created, or even how articulation can explain language structure. General issues such as the synthesis of different voices, accents, and multiple languages are discussed as special challenges facing the speech synthesis community.

Research in speech communication.

Advances in digital speech processing are now supporting application and deployment of a variety of speech technologies for human/machine communication. In fact, new businesses are rapidly forming about these technologies. But these capabilities are of little use unless society can afford them. Happily, explosive advances in microelectronics over the past two decades have assured affordable access to this sophistication as well as to the underlying computing technology. The research challenges in speech processing remain in the traditionally identified areas of recognition, synthesis, and coding. These three areas have typically been addressed individually, often with significant isolation among the efforts. But they are all facets of the same fundamental issue--how to represent and quantify the information in the speech signal. This implies deeper understanding of the physics of speech production, the constraints that the conventions of language impose, and the mechanism for information processing in the auditory system. In ongoing research, therefore, we seek more accurate models of speech generation, better computational formulations of language, and realistic perceptual guides for speech processing--along with ways to coalesce the fundamental issues of recognition, synthesis, and coding. Successful solution will yield the long-sought dictation machine, high-quality synthesis from text, and the ultimate in low bit-rate transmission of speech. It will also open the door to language-translating telephony, where the synthetic foreign translation can be in the voice of the originating talker.

Training and search methods for speech recognition.

Speech recognition involves three processes: extraction of acoustic indices from the speech signal, estimation of the probability that the observed index string was caused by a hypothesized utterance segment, and determination of the recognized utterance via a search among hypothesized alternatives. This paper is not concerned with the first process. Estimation of the probability of an index string involves a model of index production by any given utterance segment (e.g., a word). Hidden Markov models (HMMs) are used for this purpose [Makhoul, J. & Schwartz, R. (1995) Proc. Natl. Acad. Sci. USA 92, 9956-9963]. Their parameters are state transition probabilities and output probability distributions associated with the transitions. The Baum algorithm that obtains the values of these parameters from speech data via their successive reestimation will be described in this paper. The recognizer wishes to find the most probable utterance that could have caused the observed acoustic index string. That probability is the product of two factors: the probability that the utterance will produce the string and the probability that the speaker will wish to produce the utterance (the language model probability). Even if the vocabulary size is moderate, it is impossible to search for the utterance exhaustively. One practical algorithm is described [Viterbi, A. J. (1967) IEEE Trans. Inf. Theory IT-13, 260-267] that, given the index string, has a high likelihood of finding the most probable utterance.

Models of natural language understanding.

This paper surveys some of the fundamental problems in natural language (NL) understanding (syntax, semantics, pragmatics, and discourse) and the current approaches to solving them. Some recent developments in NL processing include increased emphasis on corpus-based rather than example- or intuition-based work, attempts to measure the coverage and effectiveness of NL systems, dealing with discourse and dialogue phenomena, and attempts to use both analytic and stochastic knowledge. Critical areas for the future include grammars that are appropriate to processing large amounts of real language; automatic (or at least semi-automatic) methods for deriving models of syntax, semantics, and pragmatics; self-adapting systems; and integration with speech processing. Of particular importance are techniques that can be tuned to such requirements as full versus partial understanding and spoken language versus text. Portability (the ease with which one can configure an NL system for a particular application) is one of the largest barriers to application of this technology.

Processing of speech signals for physical and sensory disabilities.

Assistive technology involving voice communication is used primarily by people who are deaf, hard of hearing, or who have speech and/or language disabilities. It is also used to a lesser extent by people with visual or motor disabilities. A very wide range of devices has been developed for people with hearing loss. These devices can be categorized not only by the modality of stimulation [i.e., auditory, visual, tactile, or direct electrical stimulation of the auditory nerve (auditory-neural)] but also in terms of the degree of speech processing that is used. At least four such categories can be distinguished: assistive devices (a) that are not designed specifically for speech, (b) that take the average characteristics of speech into account, (c) that process articulatory or phonetic characteristics of speech, and (d) that embody some degree of automatic speech recognition. Assistive devices for people with speech and/or language disabilities typically involve some form of speech synthesis or symbol generation for severe forms of language disability. Speech synthesis is also used in text-to-speech systems for sightless persons. Other applications of assistive technology involving voice communication include voice control of wheelchairs and other devices for people with mobility disabilities.

Commercial applications of speech interface technology: an industry at the threshold.

Speech interface technology, which includes automatic speech recognition, synthetic speech, and natural language processing, is beginning to have a significant impact on business and personal computer use. Today, powerful and inexpensive microprocessors and improved algorithms are driving commercial applications in computer command, consumer, data entry, speech-to-text, telephone, and voice verification. Robust speaker-independent recognition systems for command and navigation in personal computers are now available; telephone-based transaction and database inquiry systems using both speech synthesis and recognition are coming into use. Large-vocabulary speech interface systems for document creation and read-aloud proofing are expanding beyond niche markets. Today's applications represent a small preview of a rich future for speech interface technology that will eventually replace keyboards with microphones and loud-speakers to give easy accessibility to increasingly intelligent machines.