Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"speech": models, code, and papers

A Grounded Unsupervised Universal Part-of-Speech Tagger for Low-Resource Languages

Apr 10, 2019
Ronald Cardenas, Ying Lin, Heng Ji, Jonathan May

Unsupervised part of speech (POS) tagging is often framed as a clustering problem, but practical taggers need to \textit{ground} their clusters as well. Grounding generally requires reference labeled data, a luxury a low-resource language might not have. In this work, we describe an approach for low-resource unsupervised POS tagging that yields fully grounded output and requires no labeled training data. We find the classic method of Brown et al. (1992) clusters well in our use case and employ a decipherment-based approach to grounding. This approach presumes a sequence of cluster IDs is a `ciphertext' and seeks a POS tag-to-cluster ID mapping that will reveal the POS sequence. We show intrinsically that, despite the difficulty of the task, we obtain reasonable performance across a variety of languages. We also show extrinsically that incorporating our POS tagger into a name tagger leads to state-of-the-art tagging performance in Sinhalese and Kinyarwanda, two languages with nearly no labeled POS data available. We further demonstrate our tagger's utility by incorporating it into a true `zero-resource' variant of the Malopa (Ammar et al., 2016) dependency parser model that removes the current reliance on multilingual resources and gold POS tags for new languages. Experiments show that including our tagger makes up much of the accuracy lost when gold POS tags are unavailable.

* NAACL-HLT 2019, 12 pages, code available at https://github.com/isi-nlp/universal-cipher-pos-tagging 

  Access Paper or Ask Questions

POSSCORE: A Simple Yet Effective Evaluation of Conversational Search with Part of Speech Labelling

Sep 07, 2021
Zeyang Liu, Ke Zhou, Jiaxin Mao, Max L. Wilson

Conversational search systems, such as Google Assistant and Microsoft Cortana, provide a new search paradigm where users are allowed, via natural language dialogues, to communicate with search systems. Evaluating such systems is very challenging since search results are presented in the format of natural language sentences. Given the unlimited number of possible responses, collecting relevance assessments for all the possible responses is infeasible. In this paper, we propose POSSCORE, a simple yet effective automatic evaluation method for conversational search. The proposed embedding-based metric takes the influence of part of speech (POS) of the terms in the response into account. To the best knowledge, our work is the first to systematically demonstrate the importance of incorporating syntactic information, such as POS labels, for conversational search evaluation. Experimental results demonstrate that our metrics can correlate with human preference, achieving significant improvements over state-of-the-art baseline metrics.

* 11 pages 

  Access Paper or Ask Questions

End-to-End Text-to-Speech using Latent Duration based on VQ-VAE

Oct 19, 2020
Yusuke Yasuda, Xin Wang, Junichi Yamagishi

Explicit duration modeling is a key to achieving robust and efficient alignment in text-to-speech synthesis (TTS). We propose a new TTS framework using explicit duration modeling that incorporates duration as a discrete latent variable to TTS and enables joint optimization of whole modules from scratch. We formulate our method based on conditional VQ-VAE to handle discrete duration in a variational autoencoder and provide a theoretical explanation to justify our method. In our framework, a connectionist temporal classification-based force aligner acts as the approximate posterior, and text-to-duration works as the prior in the variational autoencoder. We evaluated our proposed method with a listening test and compared it with other TTS methods based on soft-attention or explicit duration modeling. The result show that our systems rated between soft-attention-based methods (Transformer-TTS, Tacotron2) and explicit duration modeling-based methods (Fastspeech).


  Access Paper or Ask Questions

Causal-Anticausal Decomposition of Speech using Complex Cepstrum for Glottal Source Estimation

Dec 30, 2019
Thomas Drugman, Baris Bozkurt, Thierry Dutoit

Complex cepstrum is known in the literature for linearly separating causal and anticausal components. Relying on advances achieved by the Zeros of the Z-Transform (ZZT) technique, we here investigate the possibility of using complex cepstrum for glottal flow estimation on a large-scale database. Via a systematic study of the windowing effects on the deconvolution quality, we show that the complex cepstrum causal-anticausal decomposition can be effectively used for glottal flow estimation when specific windowing criteria are met. It is also shown that this complex cepstral decomposition gives similar glottal estimates as obtained with the ZZT method. However, as complex cepstrum uses FFT operations instead of requiring the factoring of high-degree polynomials, the method benefits from a much higher speed. Finally in our tests on a large corpus of real expressive speech, we show that the proposed method has the potential to be used for voice quality analysis.


  Access Paper or Ask Questions

Non-autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition

Sep 14, 2021
Chuan-Fei Zhang, Yan Liu, Tian-Hao Zhang, Song-Lu Chen, Feng Chen, Xu-Cheng Yin

Non-autoregressive (NAR) transformer models have been studied intensively in automatic speech recognition (ASR), and a substantial part of NAR transformer models is to use the casual mask to limit token dependencies. However, the casual mask is designed for the left-to-right decoding process of the non-parallel autoregressive (AR) transformer, which is inappropriate for the parallel NAR transformer since it ignores the right-to-left contexts. Some models are proposed to utilize right-to-left contexts with an extra decoder, but these methods increase the model complexity. To tackle the above problems, we propose a new non-autoregressive transformer with a unified bidirectional decoder (NAT-UBD), which can simultaneously utilize left-to-right and right-to-left contexts. However, direct use of bidirectional contexts will cause information leakage, which means the decoder output can be affected by the character information from the input of the same position. To avoid information leakage, we propose a novel attention mask and modify vanilla queries, keys, and values matrices for NAT-UBD. Experimental results verify that NAT-UBD can achieve character error rates (CERs) of 5.0%/5.5% on the Aishell1 dev/test sets, outperforming all previous NAR transformer models. Moreover, NAT-UBD can run 49.8x faster than the AR transformer baseline when decoding in a single step.

* 5 pages, 3 figures. Paper submitted to ICASSP 2022 

  Access Paper or Ask Questions

Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders

Aug 15, 2021
Jing Li, Di Kang, Wenjie Pei, Xuefei Zhe, Ying Zhang, Zhenyu He, Linchao Bao

Generating conversational gestures from speech audio is challenging due to the inherent one-to-many mapping between audio and body motions. Conventional CNNs/RNNs assume one-to-one mapping, and thus tend to predict the average of all possible target motions, resulting in plain/boring motions during inference. In order to overcome this problem, we propose a novel conditional variational autoencoder (VAE) that explicitly models one-to-many audio-to-motion mapping by splitting the cross-modal latent code into shared code and motion-specific code. The shared code mainly models the strong correlation between audio and motion (such as the synchronized audio and motion beats), while the motion-specific code captures diverse motion information independent of the audio. However, splitting the latent code into two parts poses training difficulties for the VAE model. A mapping network facilitating random sampling along with other techniques including relaxed motion loss, bicycle constraint, and diversity loss are designed to better train the VAE. Experiments on both 3D and 2D motion datasets verify that our method generates more realistic and diverse motions than state-of-the-art methods, quantitatively and qualitatively. Finally, we demonstrate that our method can be readily used to generate motion sequences with user-specified motion clips on the timeline. Code and more results are at https://jingli513.github.io/audio2gestures.


  Access Paper or Ask Questions

A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition

Jul 10, 2019
Wei Zhang, Xiaodong Cui, Ulrich Finkler, George Saon, Abdullah Kayi, Alper Buyuktosunoglu, Brian Kingsbury, David Kung, Michael Picheny

Modern Automatic Speech Recognition (ASR) systems rely on distributed deep learning to for quick training completion. To enable efficient distributed training, it is imperative that the training algorithms can converge with a large mini-batch size. In this work, we discovered that Asynchronous Decentralized Parallel Stochastic Gradient Descent (ADPSGD) can work with much larger batch size than commonly used Synchronous SGD (SSGD) algorithm. On commonly used public SWB-300 and SWB-2000 ASR datasets, ADPSGD can converge with a batch size 3X as large as the one used in SSGD, thus enable training at a much larger scale. Further, we proposed a Hierarchical-ADPSGD (H-ADPSGD) system in which learners on the same computing node construct a super learner via a fast allreduce implementation, and super learners deploy ADPSGD algorithm among themselves. On a 64 Nvidia V100 GPU cluster connected via a 100Gb/s Ethernet network, our system is able to train SWB-2000 to reach a 7.6% WER on the Hub5-2000 Switchboard (SWB) test-set and a 13.2% WER on the Call-home (CH) test-set in 5.2 hours. To the best of our knowledge, this is the fastest ASR training system that attains this level of model accuracy for SWB-2000 task to be ever reported in the literature.

* INTERSPEECH 2019 

  Access Paper or Ask Questions

A Light Sliding-Window Part-of-Speech Tagger for the Apertium Free/Open-Source Machine Translation Platform

Sep 18, 2015
Gang Chen, Mikel L. Forcada

This paper describes a free/open-source implementation of the light sliding-window (LSW) part-of-speech tagger for the Apertium free/open-source machine translation platform. Firstly, the mechanism and training process of the tagger are reviewed, and a new method for incorporating linguistic rules is proposed. Secondly, experiments are conducted to compare the performances of the tagger under different window settings, with or without Apertium-style "forbid" rules, with or without Constraint Grammar, and also with respect to the traditional HMM tagger in Apertium.


  Access Paper or Ask Questions

WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit

Mar 29, 2022
Binbin Zhang, Di Wu, Zhendong Peng, Xingchen Song, Zhuoyuan Yao, Hang Lv, Lei Xie, Chao Yang, Fuping Pan, Jianwei Niu

Recently, we made available WeNet, a production-oriented end-to-end speech recognition toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address the streaming and non-streaming decoding modes in a single model. To further improve ASR performance and facilitate various production requirements, in this paper, we present WeNet 2.0 with four important updates. (1) We propose U2++, a unified two-pass framework with bidirectional attention decoders, which includes the future contextual information by a right-to-left attention decoder to improve the representative ability of the shared encoder and the performance during the rescoring stage. (2) We introduce an n-gram based language model and a WFST-based decoder into WeNet 2.0, promoting the use of rich text data in production scenarios. (3) We design a unified contextual biasing framework, which leverages user-specific context (e.g., contact lists) to provide rapid adaptation ability for production and improves ASR accuracy in both with-LM and without-LM scenarios. (4) We design a unified IO to support large-scale data for effective model training. In summary, the brand-new WeNet 2.0 achieves up to 10\% relative recognition performance improvement over the original WeNet on various corpora and makes available several important production-oriented features.


  Access Paper or Ask Questions

<<
521
522
523
524
525
526
527
528
529
530
531
532
533
>>