Creating a spontaneous conversational speech corpus

Speech recognition and language analysis of spontaneous speech arising in naturally spoken conversations are becoming the subject of much research. However, there is a shortage of spontaneous speech corpora that are freely available for academics. We therefore undertook the building of a natural conversation speech database, recording over 200 hours of conversations in English by over 600 local university students. With few exceptions, the students used their own cell phones from their own rooms or homes to speak to one another, and they were permitted to speak on any topic they chose. Although they knew that they were being recorded and that they would receive a small payment, their conversations in the corpus are probably very close to being natural and spontaneous. This paper describes a detailed case study of the problems we faced and the methods we used to make the recordings and control the collection of these social science data on a limited budget.

CLOSE—A Data-Driven Approach to Speech Separation

This paper studies single-channel speech separation, assuming unknown, arbitrary temporal dynamics for the speech signals to be separated. A data-driven approach is described, which matches each mixed speech segment against a composite training segment to separate the underlying clean speech segments. To advance the separation accuracy, the new approach seeks and separates the longest mixed speech segments with matching composite training segments. Lengthening the mixed speech segments to match reduces the uncertainty of the constituent training segments, and hence the error of separation. For convenience, we call the new approach Composition of Longest Segments, or CLOSE. The CLOSE method includes a data-driven approach to model long-range temporal dynamics of speech signals, and a statistical approach to identify the longest mixed speech segments with matching composite training segments. Experiments are conducted on the Wall Street Journal database, for separating mixtures of two simultaneous large-vocabulary speech utterances spoken by two different speakers. The results are evaluated using various objective and subjective measures, including the challenge of large-vocabulary continuous speech recognition. It is shown that the new separation approach leads to significant improvement in all these measures.

Combining missing-feature theory, speech enhancement, and speaker-dependent/-independent modeling for speech separation

This paper considers the separation and recognition of overlapped speech sentences assuming single-channel observation. A system based on a combination of several different techniques is proposed. The system uses a missing-feature approach for improving crosstalk/noise robustness, a Wiener filter for speech enhancement, hidden Markov models for speech reconstruction, and speaker-dependent/-independent modeling for speaker and speech recognition. We develop the system on the Speech Separation Challenge database, involving a task of separating and recognizing two mixing sentences without assuming advanced knowledge about the identity of the speakers nor about the signal-to-noise ratio. The paper is an extended version of a previous conference paper submitted for the challenge.

Speech Enhancement from Additive Noise and Channel Distortion - a Corpus-Based Approach

This paper presents a new approach to single-channel speech enhancement involving both noise and channel distortion (i.e., convolutional noise). The approach is based on finding longest matching segments (LMS) from a corpus of clean, wideband speech. The approach adds three novel developments to our previous LMS research. First, we address the problem of channel distortion as well as additive noise. Second, we present an improved method for modeling noise. Third, we present an iterative algorithm for improved speech estimates. In experiments using speech recognition as a test with the Aurora 4 database, the use of our enhancement approach as a preprocessor for feature extraction significantly improved the performance of a baseline recognition system. In another comparison against conventional enhancement algorithms, both the PESQ and the segmental SNR ratings of the LMS algorithm were superior to the other methods for noisy speech enhancement. Index Terms: corpus-based speech model, longest matching segment, speech enhancement, speech recognition

Adaptive modeling and high quality spectral estimation for speech enhancement

In this work an adaptive modeling and spectral estimation scheme based on a dual Discrete Kalman Filtering (DKF) is proposed for speech enhancement. Both speech and noise signals are modeled by an autoregressive structure which provides an underlying time frame dependency and improves time-frequency resolution. The model parameters are arranged to obtain a combined state-space model and are also used to calculate instantaneous power spectral density estimates. The speech enhancement is performed by a dual discrete Kalman filter that simultaneously gives estimates for the models and the signals. This approach is particularly useful as a pre-processing module for parametric based speech recognition systems that rely on spectral time dependent models. The system performance has been evaluated by a set of human listeners and by spectral distances. In both cases the use of this pre-processing module has led to improved results.

Malayalam Isolated Digit Recognition using HMM and PLP cepstral coefficient

Development of Malayalam speech recognition system is in its infancy stage; although many works have been done in other Indian languages. In this paper we present the first work on speaker independent Malayalam isolated speech recognizer based on PLP (Perceptual Linear Predictive) Cepstral Coefficient and Hidden Markov Model (HMM). The performance of the developed system has been evaluated with different number of states of HMM (Hidden Markov Model). The system is trained with 21 male and female speakers in the age group ranging from 19 to 41 years. The system obtained an accuracy of 99.5% with the unseen data

A Comparative study of HMM and SVM in Malayalam Digit Recognition

A primary medium for the human beings to communicate through language is Speech. Automatic Speech Recognition is wide spread today. Recognizing single digits is vital to a number of applications such as voice dialling of telephone numbers, automatic data entry, credit card entry, PIN (personal identification number) entry, entry of access codes for transactions, etc. In this paper we present a comparative study of SVM (Support Vector Machine) and HMM (Hidden Markov Model) to recognize and identify the digits used in Malayalam speech.

A Hybrid Architecture for Recognising Speech Signals in Malayalam

Speech is the primary, most prominent and convenient means of communication in audible language. Through speech, people can express their thoughts, feelings or perceptions by the articulation of words. Human speech is a complex signal which is non stationary in nature. It consists of immensely rich information about the words spoken, accent, attitude of the speaker, expression, intention, sex, emotion as well as style. The main objective of Automatic Speech Recognition (ASR) is to identify whatever people speak by means of computer algorithms. This enables people to communicate with a computer in a natural spoken language. Automatic recognition of speech by machines has been one of the most exciting, significant and challenging areas of research in the field of signal processing over the past five to six decades. Despite the developments and intensive research done in this area, the performance of ASR is still lower than that of speech recognition by humans and is yet to achieve a completely reliable performance level. The main objective of this thesis is to develop an efficient speech recognition system for recognising speaker independent isolated words in Malayalam.

Segmentation and Alignment of Speech and Sketching in a Design Environment

Sketches are commonly used in the early stages of design. Our previous system allows users to sketch mechanical systems that the computer interprets. However, some parts of the mechanical system might be too hard or too complicated to express in the sketch. Adding speech recognition to create a multimodal system would move us toward our goal of creating a more natural user interface. This thesis examines the relationship between the verbal and sketch input, particularly how to segment and align the two inputs. Toward this end, subjects were recorded while they sketched and talked. These recordings were transcribed, and a set of rules to perform segmentation and alignment was created. These rules represent the knowledge that the computer needs to perform segmentation and alignment. The rules successfully interpreted the 24 data sets that they were given.

From First Contact to Close Encounters: A Developmentally Deep Perceptual System for a Humanoid Robot

This thesis presents a perceptual system for a humanoid robot that integrates abilities such as object localization and recognition with the deeper developmental machinery required to forge those competences out of raw physical experiences. It shows that a robotic platform can build up and maintain a system for object localization, segmentation, and recognition, starting from very little. What the robot starts with is a direct solution to achieving figure/ground separation: it simply 'pokes around' in a region of visual ambiguity and watches what happens. If the arm passes through an area, that area is recognized as free space. If the arm collides with an object, causing it to move, the robot can use that motion to segment the object from the background. Once the robot can acquire reliable segmented views of objects, it learns from them, and from then on recognizes and segments those objects without further contact. Both low-level and high-level visual features can also be learned in this way, and examples are presented for both: orientation detection and affordance recognition, respectively. The motivation for this work is simple. Training on large corpora of annotated real-world data has proven crucial for creating robust solutions to perceptual problems such as speech recognition and face detection. But the powerful tools used during training of such systems are typically stripped away at deployment. Ideally they should remain, particularly for unstable tasks such as object detection, where the set of objects needed in a task tomorrow might be different from the set of objects needed today. The key limiting factor is access to training data, but as this thesis shows, that need not be a problem on a robotic platform that can actively probe its environment, and carry out experiments to resolve ambiguity. This work is an instance of a general approach to learning a new perceptual judgment: find special situations in which the perceptual judgment is easy and study these situations to find correlated features that can be observed more generally.

Perceptual Evaluation of Video-Realistic Speech

abstract With many visual speech animation techniques now available, there is a clear need for systematic perceptual evaluation schemes. We describe here our scheme and its application to a new video-realistic (potentially indistinguishable from real recorded video) visual-speech animation system, called Mary 101. Two types of experiments were performed: a) distinguishing visually between real and synthetic image- sequences of the same utterances, ("Turing tests") and b) gauging visual speech recognition by comparing lip-reading performance of the real and synthetic image-sequences of the same utterances ("Intelligibility tests"). Subjects that were presented randomly with either real or synthetic image-sequences could not tell the synthetic from the real sequences above chance level. The same subjects when asked to lip-read the utterances from the same image-sequences recognized speech from real image-sequences significantly better than from synthetic ones. However, performance for both, real and synthetic, were at levels suggested in the literature on lip-reading. We conclude from the two experiments that the animation of Mary 101 is adequate for providing a percept of a talking head. However, additional effort is required to improve the animation for lip-reading purposes like rehabilitation and language learning. In addition, these two tasks could be considered as explicit and implicit perceptual discrimination tasks. In the explicit task (a), each stimulus is classified directly as a synthetic or real image-sequence by detecting a possible difference between the synthetic and the real image-sequences. The implicit perceptual discrimination task (b) consists of a comparison between visual recognition of speech of real and synthetic image-sequences. Our results suggest that implicit perceptual discrimination is a more sensitive method for discrimination between synthetic and real image-sequences than explicit perceptual discrimination.

Performance of postlinguistically deaf cochlear implant patients on the connected speech test (version 3)

This paper discusses a study on postlingual cochlear implantees and the effectiveness of the CST in evaluating enhancement of speech recognition abilities.

Evaluation of multiple speech processing combinations in the Cochlear Nucleus 5 cochlear implant system using R-Space simulation

Difficulty understanding speech in the presence of background noise is a common report among cochlear implant recipients. The purpose of this research is to evaluate speech processing options currently available in the Cochlear Nucleus 5 sound processor to determine the best option for improving speech recognition in noise.

Evolvable hardware applied to voice recognition

This paper presents some results of the application on Evolvable Hardware (EHW) in the area of voice recognition. Evolvable Hardware is able to change inner connections, using genetic learning techniques, adapting its own functionality to external condition changing. This technique became feasible by the improvement of the Programmable Logic Devices. Nowadays, it is possible to have, in a single device, the ability to change, on-line and in real-time, part of its own circuit. This work proposes a reconfigurable architecture of a system that is able to receive voice commands to execute special tasks as, to help handicapped persons in their daily home routines. The idea is to collect several voice samples, process them through algorithms based on Mel - Ceptrais theory to obtain their numerical coefficients for each sample, which, compose the universe of search used by genetic algorithm. The voice patterns considered, are limited to seven sustained Portuguese vowel phonemes (a, eh, e, i, oh, o, u).

Speech Intelligibility in Noise With a Pinna Effect Imitating Cochlear Implant Processor.

OBJECTIVE To evaluate the speech intelligibility in noise with a new cochlear implant (CI) processor that uses a pinna effect imitating directional microphone system. STUDY DESIGN Prospective experimental study. SETTING Tertiary referral center. PATIENTS Ten experienced, unilateral CI recipients with bilateral severe-to-profound hearing loss. INTERVENTION All participants performed speech in noise tests with the Opus 2 processor (omnidirectional microphone mode only) and the newer Sonnet processor (omnidirectional and directional microphone mode). MAIN OUTCOME MEASURE The speech reception threshold (SRT) in noise was measured in four spatial settings. The test sentences were always presented from the front. The noise was arriving either from the front (S0N0), the ipsilateral side of the CI (S0NIL), the contralateral side of the CI (S0NCL), or the back (S0N180). RESULTS The directional mode improved the SRTs by 3.6 dB (p < 0.01), 2.2 dB (p < 0.01), and 1.3 dB (p < 0.05) in the S0N180, S0NIL, and S0NCL situations, when compared with the Sonnet in the omnidirectional mode. There was no statistically significant difference in the S0N0 situation. No differences between the Opus 2 and the Sonnet in the omnidirectional mode were observed. CONCLUSION Speech intelligibility with the Sonnet system was statistically different to speech recognition with the Opus 2 system suggesting that CI users might profit from the pinna effect imitating directionality mode in noisy environments.