Powerful and Extensible WFST Framework for Rnn-Transducer Losses (original) (raw)
Related papers
Efficient Minimum Word Error Rate Training of RNN-Transducer for End-to-End Speech Recognition
Interspeech 2020, 2020
In this work, we propose a novel and efficient minimum word error rate (MWER) training method for RNN-Transducer (RNN-T). Unlike previous work on this topic, which performs on-the-fly limited-size beam-search decoding and generates alignment scores for expected edit-distance computation, in our proposed method, we recalculate and sum scores of all the possible alignments for each hypothesis in N-best lists. The hypothesis probability scores and back-propagated gradients are calculated efficiently using the forward-backward algorithm. Moreover, the proposed method allows us to decouple the decoding and training processes, and thus we can perform offline parallel-decoding and MWER training for each subset iteratively. Experimental results show that this proposed semi-on-the-fly method can speed up the on-the-fly method by 6 times and result in a similar WER improvement (3.6%) over a baseline RNN-T model. The proposed MWER training can also effectively reduce high-deletion errors (9.2% WER-reduction) introduced by RNN-T models when EOS is added for endpointer. Further improvement can be achieved if we use a proposed RNN-T rescoring method to re-rank hypotheses and use external RNN-LM to perform additional rescoring. The best system achieves a 5% relative improvement on an English test-set of real far-field recordings and a 11.6% WER reduction on music-domain utterances.
Improving RNN-T ASR Accuracy Using Untranscribed Context Audio
ArXiv, 2020
We present a new training scheme for streaming automatic speech recognition (ASR) based on recurrent neural network transducers (RNN-T) which allows the encoder network to benefit from longer audio streams as input, while only requiring partial transcriptions of such streams during training. We show that this extension of the acoustic context during training and inference can lead to word error rate reductions of more than 6% in a realistic production setting. We investigate its effect on acoustically challenging data containing background speech and present data points which indicate that this approach helps the network learn both speaker and environment adaptation. Finally, we visualize RNN-T loss gradients with respect to the input features in order to illustrate the ability of a long short-term memory (LSTM) based ASR encoder to exploit long-term context.
arXiv (Cornell University), 2022
The recurrent neural network transducer (RNN-T) is a prominent streaming end-to-end (E2E) ASR technology. In RNN-T, the acoustic encoder commonly consists of stacks of LSTMs. Very recently, as an alternative to LSTM layers, the Conformer architecture was introduced where the encoder of RNN-T is replaced with a modified Transformer encoder composed of convolutional layers at the frontend and between attention layers. In this paper, we introduce a new streaming ASR model, Convolutional Augmented Recurrent Neural Network Transducers (ConvRNN-T) in which we augment the LSTM-based RNN-T with a novel convolutional frontend consisting of local and global context CNN encoders. ConvRNN-T takes advantage of causal 1-D convolutional layers, squeeze-and-excitation, dilation, and residual blocks to provide both global and local audio context representation to LSTM layers. We show ConvRNN-T outperforms RNN-T, Conformer, and ContextNet on Librispeech and in-house data. In addition, ConvRNN-T offers less computational complexity compared to Conformer. ConvRNN-T's superior accuracy along with its low footprint make it a promising candidate for on-device streaming ASR technologies.
RASR/NN: The RWTH neural network toolkit for speech recognition
2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014
This paper describes the new release of RASR-the open source version of the well-proven speech recognition toolkit developed and used at RWTH Aachen University. The focus is put on the implementation of the NN module for training neural network acoustic models. We describe code design, configuration, and features of the NN module. The key feature is a high flexibility regarding the network topology, choice of activation functions, training criteria, and optimization algorithm, as well as a built-in support for efficient GPU computing. The evaluation of run-time performance and recognition accuracy is performed exemplary with a deep neural network as acoustic model in a hybrid NN/HMM system. The results show that RASR achieves a state-of-the-art performance on a real-world large vocabulary task, while offering a complete pipeline for building and applying large scale speech recognition systems.
DeepSpeech: Scaling up end-to-end speech recognition
We present a state-of-the-art speech recognition system developed using end-toend deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, our system does not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learns a function that is robust to such effects. We do not need a phoneme dictionary, nor even the concept of a "phoneme." Key to our approach is a well-optimized RNN training system that uses multiple GPUs, as well as a set of novel data synthesis techniques that allow us to efficiently obtain a large amount of varied data for training. Our system, called DeepSpeech, outperforms previously published results on the widely studied Switchboard Hub5'00, achieving 16.5% error on the full test set. DeepSpeech also handles challenging noisy environments better than widely used, state-of-the-art commercial speech systems.
OverFlow: Putting flows on top of neural transducers for better TTS
arXiv (Cornell University), 2022
Neural HMMs are a type of neural transducer recently proposed for sequence-to-sequence modelling in text-to-speech. They combine the best features of classic statistical speech synthesis and modern neural TTS, requiring less data and fewer training updates, and are less prone to gibberish output caused by neural attention failures. In this paper, we combine neural HMM TTS with normalising flows for describing the highly non-Gaussian distribution of speech acoustics. The result is a powerful, fully probabilistic model of durations and acoustics that can be trained using exact maximum likelihood. Compared to dominant flow-based acoustic models, our approach integrates autoregression for improved modelling of long-range dependences such as utterance-level prosody. Experiments show that a system based on our proposal gives more accurate pronunciations and better subjective speech quality than comparable methods, whilst retaining the original advantages of neural HMMs.
Espresso: A Fast End-to-end Neural Speech Recognition Toolkit
arXiv (Cornell University), 2019
We present ESPRESSO, an open-source, modular, extensible endto-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neural machine translation toolkit FAIRSEQ. ESPRESSO supports distributed training across GPUs and computing nodes, and features various decoding approaches commonly employed in ASR, including look-ahead word-based language model fusion, for which a fast, parallelized decoder is implemented. ESPRESSO achieves state-of-the-art ASR performance on the WSJ, LibriSpeech, and Switchboard data sets among other end-to-end systems without data augmentation, and is 4-11× faster for decoding than similar systems (e.g. ESPNET).
WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit
Interspeech 2022
Recently, we made available WeNet [1], 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-toleft 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 WFSTbased 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.
Pushing the limits of RNN Compression
2019 Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing - NeurIPS Edition (EMC2-NIPS), 2019
Recurrent Neural Networks (RNN) can be difficult to deploy on resource constrained devices due to their size. As a result, there is a need for compression techniques that can significantly compress RNNs without negatively impacting task accuracy. This paper introduces a method to compress RNNs for resource constrained environments using Kronecker product (KP). KPs can compress RNN layers by 16 − 38× with minimal accuracy loss. We show that KP can beat the task accuracy achieved by other state-of-the-art compression techniques across 4 benchmarks spanning 3 different applications, while simultaneously improving inference run-time.
Improving RNN-T ASR Accuracy Using Context Audio
Interspeech 2021, 2021
We present a training scheme for streaming automatic speech recognition (ASR) based on recurrent neural network transducers (RNN-T) which allows the encoder network to learn to exploit context audio from a stream, using segmented or partially labeled sequences of the stream during training. We show that the use of context audio during training and inference can lead to word error rate reductions of more than 6% in a realistic production setting for a voice assistant ASR system. We investigate the effect of the proposed training approach on acoustically challenging data containing background speech and present data points which indicate that this approach helps the network learn both speaker and environment adaptation. To gain further insight into the ability of a long short-term memory (LSTM) based ASR encoder to exploit long-term context, we also visualize RNN-T loss gradients with respect to the input.