Emotional speech: towards a new generation of databases

Research on speech and emotion is moving from a period of exploratory research into one where there is a prospect of substantial applications, notably in human-computer interaction. Progress in the area relies heavily on the development of appropriate databases. This paper addresses the issues that need to be considered in developing databases of emotional speech, and shows how the challenge of developing apropriate databases is being addressed in three major recent projects - the Belfast project, the Reading-Leeds project and the CREST-ESP project. From these and other studies the paper draws together the tools and methods that have been developed, addresses the problems that arise and indicates the future directions for the development of emotional speech databases.

The effect of dialect mismatch on likelihood-maximising speech enhancement for noise-robust speech recognition

Traditional speech enhancement methods optimise signal-level criteria such as signal-to-noise ratio, but these approaches are sub-optimal for noise-robust speech recognition. Likelihood-maximising (LIMA) frameworks are an alternative that optimise parameters of enhancement algorithms based on state sequences generated for utterances with known transcriptions. Previous reports of LIMA frameworks have shown significant promise for improving speech recognition accuracies under additive background noise for a range of speech enhancement techniques. In this paper we discuss the drawbacks of the LIMA approach when multiple layers of acoustic mismatch are present – namely background noise and speaker accent. Experimentation using LIMA-based Mel-filterbank noise subtraction on American and Australian English in-car speech databases supports this discussion, demonstrating that inferior speech recognition performance occurs when a second layer of mismatch is seen during evaluation.

Developing a Child Friendly Text-to-Speech System

This paper discusses the implementation details of a child friendly, good quality, English text-to-speech (TTS) system that is phoneme-based, concatenative, easy to set up and use with little memory. Direct waveform concatenation and linear prediction coding (LPC) are used. Most existing TTS systems are unit-selection based, which use standard speech databases available in neutral adult voices.Here reduced memory is achieved by the concatenation of phonemes and by replacing phonetic wave files with their LPC coefficients. Linguistic analysis was used to reduce the algorithmic complexity instead of signal processing techniques. Sufficient degree of customization and generalization catering to the needs of the child user had been included through the provision for vocabulary and voice selection to suit the requisites of the child. Prosody had also been incorporated. This inexpensive TTS systemwas implemented inMATLAB, with the synthesis presented by means of a graphical user interface (GUI), thus making it child friendly. This can be used not only as an interesting language learning aid for the normal child but it also serves as a speech aid to the vocally disabled child. The quality of the synthesized speech was evaluated using the mean opinion score (MOS).

The QUT-NOISE-TIMIT corpus for the evaluation of voice activity detection algorithms

The QUT-NOISE-TIMIT corpus consists of 600 hours of noisy speech sequences designed to enable a thorough evaluation of voice activity detection (VAD) algorithms across a wide variety of common background noise scenarios. In order to construct the final mixed-speech database, a collection of over 10 hours of background noise was conducted across 10 unique locations covering 5 common noise scenarios, to create the QUT-NOISE corpus. This background noise corpus was then mixed with speech events chosen from the TIMIT clean speech corpus over a wide variety of noise lengths, signal-to-noise ratios (SNRs) and active speech proportions to form the mixed-speech QUT-NOISE-TIMIT corpus. The evaluation of five baseline VAD systems on the QUT-NOISE-TIMIT corpus is conducted to validate the data and show that the variety of noise available will allow for better evaluation of VAD systems than existing approaches in the literature.

The QUT-NOISE-SRE protocol for the evaluation of noisy speaker recognition

The QUT-NOISE-SRE protocol is designed to mix the large QUT-NOISE database, consisting of over 10 hours of back- ground noise, collected across 10 unique locations covering 5 common noise scenarios, with commonly used speaker recognition datasets such as Switchboard, Mixer and the speaker recognition evaluation (SRE) datasets provided by NIST. By allowing common, clean, speech corpora to be mixed with a wide variety of noise conditions, environmental reverberant responses, and signal-to-noise ratios, this protocol provides a solid basis for the development, evaluation and benchmarking of robust speaker recognition algorithms, and is freely available to download alongside the QUT-NOISE database. In this work, we use the QUT-NOISE-SRE protocol to evaluate a state-of-the-art PLDA i-vector speaker recognition system, demonstrating the importance of designing voice-activity-detection front-ends specifically for speaker recognition, rather than aiming for perfect coherence with the true speech/non-speech boundaries.

Detection of the closure-burst transitions of stops and affricates in continuous speech using the plosion index

Automatic and accurate detection of the closure-burst transition events of stops and affricates serves many applications in speech processing. A temporal measure named the plosion index is proposed to detect such events, which are characterized by an abrupt increase in energy. Using the maxima of the pitch-synchronous normalized cross correlation as an additional temporal feature, a rule-based algorithm is designed that aims at selecting only those events associated with the closure-burst transitions of stops and affricates. The performance of the algorithm, characterized by receiver operating characteristic curves and temporal accuracy, is evaluated using the labeled closure-burst transitions of stops and affricates of the entire TIMIT test and training databases. The robustness of the algorithm is studied with respect to global white and babble noise as well as local noise using the TIMIT test set and on telephone quality speech using the NTIMIT test set. For these experiments, the proposed algorithm, which does not require explicit statistical training and is based on two one-dimensional temporal measures, gives a performance comparable to or better than the state-of-the-art methods. In addition, to test the scalability, the algorithm is applied on the Buckeye conversational speech corpus and databases of two Indian languages. (C) 2014 Acoustical Society of America.

A fast algorithm for speech polarity detection using long-term linear prediction

Speech polarity detection is a crucial first step in many speech processing techniques. In this paper, an algorithm is proposed that improvises the existing technique using the skewness of the voice source (VS) signal. Here, the integrated linear prediction residual (ILPR) is used as the VS estimate, which is obtained using linear prediction on long-term frames of the low-pass filtered speech signal. This excludes the unvoiced regions from analysis and also reduces the computation. Further, a modified skewness measure is proposed for decision, which also considers the magnitude of the skewness of the ILPR along with its sign. With the detection error rate (DER) as the performance metric, the algorithm is tested on 8 large databases and its performance (DER=0.20%) is found to be comparable to that of the best technique (DER=0.06%) on both clean and noisy speech. Further, the proposed method is found to be ten times faster than the best technique.

Major and minor music compared to excited and subdued speech.

The affective impact of music arises from a variety of factors, including intensity, tempo, rhythm, and tonal relationships. The emotional coloring evoked by intensity, tempo, and rhythm appears to arise from association with the characteristics of human behavior in the corresponding condition; however, how and why particular tonal relationships in music convey distinct emotional effects are not clear. The hypothesis examined here is that major and minor tone collections elicit different affective reactions because their spectra are similar to the spectra of voiced speech uttered in different emotional states. To evaluate this possibility the spectra of the intervals that distinguish major and minor music were compared to the spectra of voiced segments in excited and subdued speech using fundamental frequency and frequency ratios as measures. Consistent with the hypothesis, the spectra of major intervals are more similar to spectra found in excited speech, whereas the spectra of particular minor intervals are more similar to the spectra of subdued speech. These results suggest that the characteristic affective impact of major and minor tone collections arises from associations routinely made between particular musical intervals and voiced speech.

Robust bimodal person identification using face and speech with limited training data and corruption of both modalities

This paper presents a novel method of audio-visual fusion for person identification where both the speech and facial modalities may be corrupted, and there is a lack of prior knowledge about the corruption. Furthermore, we assume there is a limited amount of training data for each modality (e.g., a short training speech segment and a single training facial image for each person). A new representation and a modified cosine similarity are introduced for combining and comparing bimodal features with limited training data as well as vastly differing data rates and feature sizes. Optimal feature selection and multicondition training are used to reduce the mismatch between training and testing, thereby making the system robust to unknown bimodal corruption. Experiments have been carried out on a bimodal data set created from the SPIDRE and AR databases with variable noise corruption of speech and occlusion in the face images. The new method has demonstrated improved recognition accuracy.

Speech-language therapy for treatment of dysphagia and dysphonia in systemic granulomatous diseases: granulomatous diseases: dysphagia and dysphonia treatments

The granulomatous lesions are frequently founded in infectious diseases and can involve the larynx and pharynx and can cause varying degrees of dysphonia and dysphagia. There is still no systematic review that analyzes effectiveness of speech therapy in systemic granulomatous diseases. Research strategy: A systematic review was performed according to Cochrane guideline considering the inclusion of RCTs and quasi-RCTs about the effectiveness of speech-language therapy to treat dysphagia and dysphonia symptoms in systemic granulomatous diseases of the larynx and pharynx. Selection criteria: The outcome planned to be measured in this review were: swallowing impairment, frequency of chest infections and voice and swallowing symptoms. Data analysis: We identified 1,140 citations from all electronic databases. After an initial shift we only selected 9 titles to be retrieved in full-text. After full reading, there was no RCT found in this review and therefore, we only described the existing 2 case series studies. Results: There were no randomized controlled trials found in the literature. Therefore, two studies were selected to be included only for narratively analysis as they were case series. Conclusion: There is no evidence from high quality studies about the effectiveness of speech-language therapy in patients with granulomatous diseases of the larynx and pharynx. The investigators could rely in the outcomes suggested in this review to design their own clinical trials.

ENHANCING COMMUNICATION THROUGH SUCCESSFUL REPAIR: EXAMINING FLUENCY AND MECHANISMS FOR SYNTACTIC PROGRESS IN APHASIC AND NON-APHASIC SPEECH

The fields of Rhetoric and Communication usually assume a competent speaker who is able to speak well with conscious intent; however, what happens when intent and comprehension are intact but communicative facilities are impaired (e.g., by stroke or traumatic brain injury)? What might a focus on communicative success be able to tell us in those instances? This project considers this question in examining communication disorders through identifying and analyzing patterns of (dis) fluent speech between 10 aphasic and 10 non-aphasic adults. The analysis in this report is centered on a collection of data provided by the Aphasia Bank database. The database’s collection protocol guides aphasic and non-aphasic participants through a series of language assessments, and for my re-analysis of the database’s transcripts I consider communicative success is and how it is demonstrated during a re-telling of the Cinderella narrative. I conducted a thorough examination of a set of participant transcripts to understand the contexts in which speech errors occur, and how (dis) fluencies may follow from aphasic and non-aphasic participant’s speech patterns. An inductive mixed-methods approach, informed by grounded theory, qualitative, and linguistic analyses of the transcripts functioned as a means to balance the classification of data, providing a foundation for all sampling decisions. A close examination of the transcripts and the codes of the Aphasia Bank database suggest that while the coding is abundant and detailed, that further levels of coding and analysis may be needed to reveal underlying similarities and differences in aphasic vs. non-aphasic linguistic behavior. Through four successive levels of increasingly detailed analysis, I found that patterns of repair by aphasics and non-aphasics differed primarily in degree rather than kind. This finding may have therapeutic impact, in reassuring aphasics that they are on the right track to achieving communicative fluency.

Analyzing training dependencies and posterior fusion in discriminant classification of apnoea patients based on sustained and connected speech

We present a novel approach using both sustained vowels and connected speech, to detect obstructive sleep apnea (OSA) cases within a homogeneous group of speakers. The proposed scheme is based on state-of-the-art GMM-based classifiers, and acknowledges specifically the way in which acoustic models are trained on standard databases, as well as the complexity of the resulting models and their adaptation to specific data. Our experimental database contains a suitable number of utterances and sustained speech from healthy (i.e control) and OSA Spanish speakers. Finally, a 25.1% relative reduction in classification error is achieved when fusing continuous and sustained speech classifiers. Index Terms: obstructive sleep apnea (OSA), gaussian mixture models (GMMs), background model (BM), classifier fusion.

Towards glottal source controllability in expressive speech synthesis

In order to obtain more human like sounding humanmachine interfaces we must first be able to give them expressive capabilities in the way of emotional and stylistic features so as to closely adequate them to the intended task. If we want to replicate those features it is not enough to merely replicate the prosodic information of fundamental frequency and speaking rhythm. The proposed additional layer is the modification of the glottal model, for which we make use of the GlottHMM parameters. This paper analyzes the viability of such an approach by verifying that the expressive nuances are captured by the aforementioned features, obtaining 95% recognition rates on styled speaking and 82% on emotional speech. Then we evaluate the effect of speaker bias and recording environment on the source modeling in order to quantify possible problems when analyzing multi-speaker databases. Finally we propose a speaking styles separation for Spanish based on prosodic features and check its perceptual significance.