Self-Expressing Autoencoders for Unsupervised Spoken Term Discovery

Unsupervised spoken term discovery consists of two tasks: finding the acoustic segment boundaries and labeling acoustically similar segments with the same labels. We perform segmentation based on the assumption that the frame feature vectors are more similar within a segment than across the segments. Therefore, for strong segmentation performance, it is crucial that the features represent the phonetic properties of a frame more than other factors of variability. We achieve this via a self-expressing autoencoder framework. It consists of a single encoder and two decoders with shared weights. The encoder projects the input features into a latent representation. One of the decoders tries to reconstruct the input from these latent representations and the other from the self-expressed version of them. We use the obtained features to segment and cluster the speech data. We evaluate the performance of the proposed method in the Zero Resource 2020 challenge unit discovery task. The proposed system consistently outperforms the baseline, demonstrating the usefulness of the method in learning representations.

[1]  Aren Jansen,et al.  Unsupervised neural network based feature extraction using weak top-down constraints , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  K. Sri Rama Murty,et al.  Unsupervised Speech Signal to Symbol Transformation for Zero Resource Speech Applications , 2017, INTERSPEECH.

[3]  Geoffrey Zweig,et al.  Transformer-Based Acoustic Modeling for Hybrid Speech Recognition , 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  Lorenzo Rosasco,et al.  Discovering discrete subword units with binarized autoencoders and hidden-Markov-model encoders , 2015, INTERSPEECH.

[5]  Edouard Grave,et al.  End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures , 2019, ArXiv.

[6]  Bogdan Ludusan,et al.  Bridging the gap between speech technology and natural language processing: an evaluation toolbox for term discovery systems , 2014, LREC.

[7]  Herman Kamper,et al.  Phoneme Based Embedded Segmental K-Means for Unsupervised Term Discovery , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  Jiucang Hao,et al.  Emotion recognition by speech signals , 2003, INTERSPEECH.

[9]  Andreas Stolcke,et al.  SRILM at Sixteen: Update and Outlook , 2011 .

[10]  Oh-Wook Kwon,et al.  EMOTION RECOGNITION BY SPEECH SIGNAL , 2003 .

[11]  K. Sri Rama Murty,et al.  Unsupervised Segmentation of Speech Signals Using Kernel-Gram Matrices , 2017, NCVPRIPG.

[12]  Karen Livescu,et al.  An embedded segmental K-means model for unsupervised segmentation and clustering of speech , 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

[13]  Tara N. Sainath,et al.  FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION Digital Object Identifier 10.1109/MSP.2012.2205597 , 2012 .

[14]  James R. Glass,et al.  A Nonparametric Bayesian Approach to Acoustic Model Discovery , 2012, ACL.

[15]  David A. van Leeuwen,et al.  Unsupervised acoustic sub-word unit detection for query-by-example spoken term detection , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[16]  Giorgio Metta,et al.  An auto-encoder based approach to unsupervised learning of subword units , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[17]  Herbert Gish,et al.  Unsupervised training of an HMM-based self-organizing unit recognizer with applications to topic classification and keyword discovery , 2014, Comput. Speech Lang..

[18]  Ewan Dunbar,et al.  A hybrid dynamic time warping-deep neural network architecture for unsupervised acoustic modeling , 2015, INTERSPEECH.

[19]  Sakriani Sakti,et al.  The Zero Resource Speech Challenge 2019: TTS without T , 2019, INTERSPEECH.

[20]  Aren Jansen,et al.  The zero resource speech challenge 2017 , 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

[21]  Aren Jansen,et al.  A segmental framework for fully-unsupervised large-vocabulary speech recognition , 2016, Comput. Speech Lang..

[22]  Najim Dehak,et al.  Unsupervised Acoustic Segmentation and Clustering Using Siamese Network Embeddings , 2019, INTERSPEECH.

[23]  Maarten Versteegh,et al.  A deep scattering spectrum — Deep Siamese network pipeline for unsupervised acoustic modeling , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[24]  Aren Jansen,et al.  Efficient spoken term discovery using randomized algorithms , 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

[25]  Aren Jansen,et al.  A comparison of neural network methods for unsupervised representation learning on the zero resource speech challenge , 2015, INTERSPEECH.

[26]  James R. Glass,et al.  Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams , 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

[27]  Erich Elsen,et al.  Deep Speech: Scaling up end-to-end speech recognition , 2014, ArXiv.

[28]  Michael C. Frank,et al.  Unsupervised word discovery from speech using automatic segmentation into syllable-like units , 2015, INTERSPEECH.

[29]  John J. Godfrey,et al.  SWITCHBOARD: telephone speech corpus for research and development , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[30]  Patrick Kenny,et al.  Front-End Factor Analysis for Speaker Verification , 2011, IEEE Transactions on Audio, Speech, and Language Processing.