Data Mining Practical Machine Learning Tools and Techniques

http://cs.uef.fi/sipu/pub/SRE-review-Kinnunen-and-Li.pdf

An overview of text-independent speaker recognition: From features to supervectors

Work on voice sciences over recent decades has led to a proliferation of acoustic parameters that are used quite selectively and are not always extracted in a similar fashion. With many independent teams working in different research areas, shared standards become an essential safeguard to ensure compliance with state-of-the-art methods allowing appropriate comparison of results across studies and potential integration and combination of extraction and recognition systems. In this paper we propose a basic standard acoustic parameter set for various areas of automatic voice analysis, such as paralinguistic or clinical speech analysis. In contrast to a large brute-force parameter set, we present a minimalistic set of voice parameters here. These were selected based on a) their potential to index affective physiological changes in voice production, b) their proven value in former studies as well as their automatic extractability, and c) their theoretical significance. The set is intended to provide a common baseline for evaluation of future research and eliminate differences caused by varying parameter sets or even different implementations of the same parameters. Our implementation is publicly available with the openSMILE toolkit. Comparative evaluations of the proposed feature set and large baseline feature sets of INTERSPEECH challenges show a high performance of the proposed set in relation to its size.

/pdf/the-geneva-minimalistic-acoustic-parameter-set-gemaps-for-36spb4mksx.pdf

The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing

Over the past decades, a tremendous amount of research has been done on the use of machine learning for speech processing applications, especially speech recognition. However, in the past few years, research has focused on utilizing deep learning for speech-related applications. This new area of machine learning has yielded far better results when compared to others in a variety of applications including speech, and thus became a very attractive area of research. This paper provides a thorough examination of the different studies that have been conducted since 2006, when deep learning first arose as a new area of machine learning, for speech applications. A thorough statistical analysis is provided in this review which was conducted by extracting specific information from 174 papers published between the years 2006 and 2018. The results provided in this paper shed light on the trends of research in this area as well as bring focus to new research topics.

/pdf/speech-recognition-using-deep-neural-networks-a-systematic-kp43ilkz5h.pdf

Speech Recognition Using Deep Neural Networks: A Systematic Review

The INTERSPEECH 2013 Computational Paralinguistics Challenge provides for the first time a unified test-bed for Social Signals such as laughter in speech. It further introduces conflict in group discussions as a new task and deals with autism and its manifestations in speech. Finally, emotion is revisited as task, albeit with a broader range of overall twelve enacted emotional states. In this paper, we describe these four Sub-Challenges, their conditions, baselines, and a new feature set by the openSMILE toolkit, provided to the participants. Index Terms: Computational Paralinguistics, Challenge, Social Signals, Conflict, Emotion, Autism

/pdf/the-interspeech-2013-computational-paralinguistics-challenge-2s3h1zujqy.pdf

The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism

Speech recognition of children is a more difficult task than speech recognition of adults. This problem is amplified for children with articulation disorders like cleft lip and palate (CLP). In this work we improved our automatic speech recognition system by integrating prior knowledge. Prior knowledge focuses on two different aspects: A test-dependent language modeling and an age-dependent acoustic modeling. These two approaches are merged at the end to different test- and age-dependent recognizers. We evaluated our system on a dataset of 35 children with CLP. Significant improvements could be found on this dataset. With our baseline system we achieved a negative word accuarcy (WA) of −11.0%. By an extended language modeling we achieved 27.5%. The age-dependent recognition system gains a huge improvement and achieves aWA of 42.6%. With the significant improvements in WA it is possible to perform an automatic detection and identification of specific words. Thus, we took the first step towards a speech assessment on word and subword level.

/pdf/improvement-of-a-speech-recognizer-for-standardized-medical-48vucxypel.pdf

Improvement of a speech recognizer for standardized medical assessment of children's speech by integration of prior knowledge

Methods, apparatus, systems and articles of manufacture are disclosed for distributed automatic speech recognition. An example apparatus includes a detector to process an input audio signal and identify a portion of the input audio signal including a sound to be evaluated, the sound to be evaluated organized into a plurality of audio features representing the sound. The example apparatus includes a quantizer to process the audio features using a quantization process to reduce the audio features to generate a reduced set of audio features for transmission. The example apparatus includes a transmitter to transmit the reduced set of audio features over a low-energy communication channel for processing.

Systems and methods for energy efficient and low power distributed automatic speech recognition on wearable devices

In this work we present an approach for text-independent speaker recognition. As features we used Mel Frequency Cepstrum Coefficients (MFCCs) and Temporal Patterns (TRAPs). For each speaker we trained Gaussian Mixture Models (GMMs) with different numbers of densities. The used database was a 36 speakers database with very noisy close-talking recordings. For the training a Universal Background Model (UBM) is built by the EM-Algorithm and all available training data. This UBM is then used to create speaker-dependent models for each speaker. This can be done in two ways: Taking the UBM as an initial model for EM-Training or Maximum-A-Posteriori (MAP) adaptation. For the 36 speaker database the use of TRAPs instead of MFCCs leads to a frame-wise recognition improvement of 12.0%. The adaptation with MAP enhanced the recognition rate by another 14.2%.

/pdf/text-independent-speaker-identification-using-temporal-1om6go3kf1.pdf

Text-independent speaker identification using temporal patterns

BACKGROUND Multimodal treatment of oral cancer can cause speech disorders and diminish speech intelligibility. Speech intelligibility is an essential part of social interaction and therefore important for coping with the disease. The aim of this study was to investigate the influence of speech intelligibility on coping strategies and a standardized questionnaire. PATIENTS AND METHODS Speech recordings from 76 patients 60.7 ± 11.4 years old (19 women, 57 men) were performed at least 6 months after multimodal treatment of T1-T4 squamous cell carcinoma of the oral cavity and evaluated by automatic speech recognition. Speech intelligibility was quantized as correctly recognized words of a standard text (word recognition rate WR). Coping was evaluated by the Trier Scales of Coping Strategies via questionnaires. RESULTS Speech intelligibility scores WR rated between 22.2% and 84.3% (mean value 54.2 ± 15.7). Coping strategies vary considerably between the patients and between the scales. WR and the Trier Scales significantly correlate in 3 of the 5 categories (Rumination, Search for Information and Exchange of Experiences). CONCLUSION Reduced speech intelligibility after multimodal treatment of oral cancer is associated with a change of coping strategy. This includes not only communication-based strategies (Search for Information and Exchange of Experiences) but also intra-psychic processes like rumination.

Sprachverständlichkeit und Krankheitsverarbeitung nach der Therapie von Mundhöhlenkarzinomen

This paper describes an approach for intent classification and tagging on embedded devices, such as smart watches. We describe a technique to train neuronal networks where the final neuronal network weights are binary. This enables memory bandwidth optimized inference and efficient computation even on constrained/embedded platforms. The flow of the approach is as follows: tf-idf word selection method reduces the number of overall weights. Bag-of-Words features are used with a feedforward and recurrent neuronal network for intent classification and tagging, respectively. A novel double Gaussian based regularization term is used to train the network. Finally, the weights are almost clipped lossless to −1 or 1 which results in a tiny binary neuronal network for intent classification and tagging. Our technique is evaluated using a text corpus of transcribed and annotated voice queries. The test domain is ”lights control”. We compare the intent and tagging accuracy of the ultra-compact binary neuronal network with our baseline system. The novel approach yields comparable accuracy but reduces the model size by a factor of 16: from 160kB to 10kB.

Tobias Bocklet

Papers

Improvement of a speech recognizer for standardized medical assessment of children's speech by integration of prior knowledge

Systems and methods for energy efficient and low power distributed automatic speech recognition on wearable devices

Text-independent speaker identification using temporal patterns

Sprachverständlichkeit und Krankheitsverarbeitung nach der Therapie von Mundhöhlenkarzinomen

Ultra-Compact NLU: Neuronal Network Binarization as Regularization.