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

Consistent Training and Decoding For End-to-end Speech Recognition Using Lattice-free MMI

Dec 30, 2021
Jinchuan Tian, Jianwei Yu, Chao Weng, Shi-Xiong Zhang, Dan Su, Dong Yu, Yuexian Zou

Recently, End-to-End (E2E) frameworks have achieved remarkable results on various Automatic Speech Recognition (ASR) tasks. However, Lattice-Free Maximum Mutual Information (LF-MMI), as one of the discriminative training criteria that show superior performance in hybrid ASR systems, is rarely adopted in E2E ASR frameworks. In this work, we propose a novel approach to integrate LF-MMI criterion into E2E ASR frameworks in both training and decoding stages. The proposed approach shows its effectiveness on two of the most widely used E2E frameworks including Attention-Based Encoder-Decoders (AEDs) and Neural Transducers (NTs). Experiments suggest that the introduction of the LF-MMI criterion consistently leads to significant performance improvements on various datasets and different E2E ASR frameworks. The best of our models achieves competitive CER of 4.1\% / 4.4\% on Aishell-1 dev/test set; we also achieve significant error reduction on Aishell-2 and Librispeech datasets over strong baselines.

  Access Paper or Ask Questions

A simple language-agnostic yet very strong baseline system for hate speech and offensive content identification

Feb 05, 2022
Yves Bestgen

For automatically identifying hate speech and offensive content in tweets, a system based on a classical supervised algorithm only fed with character n-grams, and thus completely language-agnostic, is proposed by the SATLab team. After its optimization in terms of the feature weighting and the classifier parameters, it reached, in the multilingual HASOC 2021 challenge, a medium performance level in English, the language for which it is easy to develop deep learning approaches relying on many external linguistic resources, but a far better level for the two less resourced language, Hindi and Marathi. It ends even first when performances are averaged over the three tasks in these languages, outperforming many deep learning approaches. These performances suggest that it is an interesting reference level to evaluate the benefits of using more complex approaches such as deep learning or taking into account complementary resources.

* A slightly modified version of the paper: "A simple language-agnostic yet strong baseline system for hate speech and offensive content identification. In Working Notes of FIRE 2021 - Forum for Information Retrieval Evaluation (10 p.). 

  Access Paper or Ask Questions

A novel policy for pre-trained Deep Reinforcement Learning for Speech Emotion Recognition

Jan 31, 2021
Thejan Rajapakshe, Rajib Rana, Sara Khalifa, Björn W. Schuller, Jiajun Liu

Reinforcement Learning (RL) is a semi-supervised learning paradigm which an agent learns by interacting with an environment. Deep learning in combination with RL provides an efficient method to learn how to interact with the environment is called Deep Reinforcement Learning (deep RL). Deep RL has gained tremendous success in gaming - such as AlphaGo, but its potential have rarely being explored for challenging tasks like Speech Emotion Recognition (SER). The deep RL being used for SER can potentially improve the performance of an automated call centre agent by dynamically learning emotional-aware response to customer queries. While the policy employed by the RL agent plays a major role in action selection, there is no current RL policy tailored for SER. In addition, extended learning period is a general challenge for deep RL which can impact the speed of learning for SER. Therefore, in this paper, we introduce a novel policy - "Zeta policy" which is tailored for SER and apply Pre-training in deep RL to achieve faster learning rate. Pre-training with cross dataset was also studied to discover the feasibility of pre-training the RL Agent with a similar dataset in a scenario of where no real environmental data is not available. IEMOCAP and SAVEE datasets were used for the evaluation with the problem being to recognize four emotions happy, sad, angry and neutral in the utterances provided. Experimental results show that the proposed "Zeta policy" performs better than existing policies. The results also support that pre-training can reduce the training time upon reducing the warm-up period and is robust to cross-corpus scenario.

  Access Paper or Ask Questions

Small energy masking for improved neural network training for end-to-end speech recognition

Feb 15, 2020
Chanwoo Kim, Kwangyoun Kim, Sathish Reddy Indurthi

In this paper, we present a Small Energy Masking (SEM) algorithm, which masks inputs having values below a certain threshold. More specifically, a time-frequency bin is masked if the filterbank energy in this bin is less than a certain energy threshold. A uniform distribution is employed to randomly generate the ratio of this energy threshold to the peak filterbank energy of each utterance in decibels. The unmasked feature elements are scaled so that the total sum of the feature values remain the same through this masking procedure. This very simple algorithm shows relatively 11.2 % and 13.5 % Word Error Rate (WER) improvements on the standard LibriSpeech test-clean and test-other sets over the baseline end-to-end speech recognition system. Additionally, compared to the input dropout algorithm, SEM algorithm shows relatively 7.7 % and 11.6 % improvements on the same LibriSpeech test-clean and test-other sets. With a modified shallow-fusion technique with a Transformer LM, we obtained a 2.62 % WER on the LibriSpeech test-clean set and a 7.87 % WER on the LibriSpeech test-other set.

* Accepted at ICASSP 2020 

  Access Paper or Ask Questions

Filtered Noise Shaping for Time Domain Room Impulse Response Estimation From Reverberant Speech

Jul 15, 2021
Christian J. Steinmetz, Vamsi Krishna Ithapu, Paul Calamia

Deep learning approaches have emerged that aim to transform an audio signal so that it sounds as if it was recorded in the same room as a reference recording, with applications both in audio post-production and augmented reality. In this work, we propose FiNS, a Filtered Noise Shaping network that directly estimates the time domain room impulse response (RIR) from reverberant speech. Our domain-inspired architecture features a time domain encoder and a filtered noise shaping decoder that models the RIR as a summation of decaying filtered noise signals, along with direct sound and early reflection components. Previous methods for acoustic matching utilize either large models to transform audio to match the target room or predict parameters for algorithmic reverberators. Instead, blind estimation of the RIR enables efficient and realistic transformation with a single convolution. An evaluation demonstrates our model not only synthesizes RIRs that match parameters of the target room, such as the $T_{60}$ and DRR, but also more accurately reproduces perceptual characteristics of the target room, as shown in a listening test when compared to deep learning baselines.

* Accepted to WASPAA 2021. See details at 

  Access Paper or Ask Questions

Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognition

Jun 16, 2018
Pengcheng Guo, Haihua Xu, Lei Xie, Eng Siong Chng

In this paper, we present our overall efforts to improve the performance of a code-switching speech recognition system using semi-supervised training methods from lexicon learning to acoustic modeling, on the South East Asian Mandarin-English (SEAME) data. We first investigate semi-supervised lexicon learning approach to adapt the canonical lexicon, which is meant to alleviate the heavily accented pronunciation issue within the code-switching conversation of the local area. As a result, the learned lexicon yields improved performance. Furthermore, we attempt to use semi-supervised training to deal with those transcriptions that are highly mismatched between human transcribers and ASR system. Specifically, we conduct semi-supervised training assuming those poorly transcribed data as unsupervised data. We found the semi-supervised acoustic modeling can lead to improved results. Finally, to make up for the limitation of the conventional n-gram language models due to data sparsity issue, we perform lattice rescoring using neural network language models, and significant WER reduction is obtained.

* 5pages, 3 figures, INTERSPEECH 2018 

  Access Paper or Ask Questions

Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition

Feb 19, 2020
Shuai Zhang, Jiangyan Yi, Zhengkun Tian, Jianhua Tao, Ye Bai

Recently, language identity information has been utilized to improve the performance of end-to-end code-switching (CS) speech recognition. However, previous works use an additional language identification (LID) model as an auxiliary module, which causes the system complex. In this work, we propose an improved recurrent neural network transducer (RNN-T) model with language bias to alleviate the problem. We use the language identities to bias the model to predict the CS points. This promotes the model to learn the language identity information directly from transcription, and no additional LID model is needed. We evaluate the approach on a Mandarin-English CS corpus SEAME. Compared to our RNN-T baseline, the proposed method can achieve 16.2% and 12.9% relative error reduction on two test sets, respectively.

  Access Paper or Ask Questions

Acoustic Model Optimization Based On Evolutionary Stochastic Gradient Descent with Anchors for Automatic Speech Recognition

Jul 10, 2019
Xiaodong Cui, Michael Picheny

Evolutionary stochastic gradient descent (ESGD) was proposed as a population-based approach that combines the merits of gradient-aware and gradient-free optimization algorithms for superior overall optimization performance. In this paper we investigate a variant of ESGD for optimization of acoustic models for automatic speech recognition (ASR). In this variant, we assume the existence of a well-trained acoustic model and use it as an anchor in the parent population whose good "gene" will propagate in the evolution to the offsprings. We propose an ESGD algorithm leveraging the anchor models such that it guarantees the best fitness of the population will never degrade from the anchor model. Experiments on 50-hour Broadcast News (BN50) and 300-hour Switchboard (SWB300) show that the ESGD with anchors can further improve the loss and ASR performance over the existing well-trained acoustic models.

* Interspeech 2019 

  Access Paper or Ask Questions