Language identification greatly impacts the success of downstream tasks such as automatic speech recognition. Recently, self-supervised speech representations learned by wav2vec 2.0 have been shown to be very effective for a range of speech tasks. We extend previous self-supervised work on language identification by experimenting with pre-trained models which were learned on real-world unconstrained speech in multiple languages and not just on English. We show that models pre-trained on many languages perform better and enable language identification systems that require very little labeled data to perform well. Results on a 26 languages setup show that with only 10 minutes of labeled data per language, a cross-lingually pre-trained model can achieve over 89.2% accuracy.

With 4.5 million hours of English speech from 10 different sources across 120 countries and models of up to 10 billion parameters, we explore the frontiers of scale for automatic speech recognition.We propose data selection techniques to efficiently scale training data to find the most valuable samples in massive datasets.To efficiently scale model sizes, we leverage various optimizations such as sparse transducer loss and model sharding.By training 1-10B parameter universal English ASR models, we push the limits of speech recognition performance across many domains.Furthermore, our models learn powerful speech representations with zero and few-shot capabilities on novel domains and styles of speech, exceeding previous results across multiple in-house and public benchmarks.For speakers with disorders due to brain damage, our best zero-shot and few-shot models achieve 22% and 60% relative improvement on the AphasiaBank test set, respectively, while realizing the best performance on public social media videos.Furthermore, the same universal model reaches equivalent performance with 500x less in-domain data on the SPGISpeech financial-domain dataset.

Hybrid automatic speech recognition (ASR) models are typically sequentially trained with CTC or LF-MMI criteria. However, they have vastly different legacies and are usually implemented in different frameworks. In this paper, by decoupling the concepts of modeling units and label topologies and building proper numerator/denominator graphs accordingly, we establish a generalized framework for hybrid acoustic modeling (AM). In this framework, we show that LF-MMI is a powerful training criterion applicable to both limited-context and full-context models, for wordpiece/mono-char/bi-char/chenone units, with both HMM/CTC topologies. From this framework, we propose three novel training schemes: chenone(ch)/wordpiece(wp)-CTC-bMMI, and wordpiece(wp)-HMM-bMMI with different advantages in training performance, decoding efficiency and decoding time-stamp accuracy. The advantages of different training schemes are evaluated comprehensively on Librispeech, and wp-CTC-bMMI and ch-CTC-bMMI are evaluated on two real world ASR tasks to show their effectiveness. Besides, we also show bi-char(bc) HMM-MMI models can serve as better alignment models than traditional non-neural GMM-HMMs.

This paper proposes an efficient memory transformer Emformer for low latency streaming speech recognition. In Emformer, the long-range history context is distilled into an augmented memory bank to reduce self-attention’s computation complexity. A cache mechanism saves the computation for the key and value in self-attention for the left context. Emformer applies a parallelized block processing in training to support low latency models. We carry out experiments on benchmark LibriSpeech data. Under average latency of 960 ms, Emformer gets WER 2.50% on test-clean and 5.62% on test-other. Comparing with a strong baseline augmented memory transformer (AM-TRF), Emformer gets 4.6 folds training speedup and 18% relative real-time factor (RTF) reduction in decoding with relative WER reduction 17% on test-clean and 9% on test-other. For a low latency scenario with an average latency of 80 ms, Emformer achieves WER 3.01% on test-clean and 7.09% on test-other. Comparing with the LSTM baseline with the same latency and model size, Emformer gets relative WER reduction 9% and 16% on test-clean and test-other, respectively.

Transformer-based acoustic models have shown promising results very recently. In this paper, we summarize the application of transformer and its streamable variant, Emformer based acoustic model [1] for large scale speech recognition applications. We compare the transformer based acoustic models with their LSTM counterparts on industrial scale tasks. Specifically, we compare Emformer with latency-controlled BLSTM (LCBLSTM) on medium latency tasks and LSTM on low latency tasks. On a low latency voice assistant task, Emformer gets 24% to 26% relative word error rate reductions (WERRs). For medium latency scenarios, comparing with LCBLSTM with similar model size and latency, Emformer gets significant WERR across four languages in video captioning datasets with 2-3 times inference real-time factors reduction.

End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers. Specifically, recurrent neural network transducer (RNN-T) has shown competitive ASR performance on various benchmarks. In this work, we examine ways in which RNN-T can achieve better ASR accuracy via performing auxiliary tasks. We propose (i) using the same auxiliary task as primary RNN-T ASR task, and (ii) performing context-dependent graphemic state prediction as in conventional hybrid modeling. In transcribing social media videos with varying training data size, we first evaluate the streaming ASR performance on three languages: Romanian, Turkish and German. We find that both proposed methods provide consistent improvements. Next, we observe that both auxiliary tasks demonstrate efficacy in learning deep transformer encoders for RNN-T criterion, thus achieving competitive results -2.0%/4.2% WER on LibriSpeech test-clean/other - as compared to prior top performing models.

Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation [1] and automatic speech recognition [2]. One major challenge of attention-based models is the need of access to the full sequence and the quadratically growing computational cost concerning the sequence length. These characteristics pose challenges, especially for low-latency scenarios, where the system is often required to be streaming. In this paper, we build a compact and streaming speech recognition system on top of the end-to-end neural transducer architecture [3] with attention-based modules augmented with convolution [2]. The proposed system equips the end-to-end models with the streaming capability and reduces the large footprint from the streaming attention-based model using augmented memory [4], [5]. On the LibriSpeech [6] dataset, our proposed system achieves word error rates 2.7% on test-clean and 5.8% on test-other, to our best knowledge the lowest among streaming approaches reported so far.

In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on three popular training criteria: LF-MMI, CTC and RNN-T. In transcribing social media videos of 7 languages with training data 3K - 14K hours, we conduct large-scale controlled experimentation across each criterion using identical datasets and encoder model architecture. We find that RNN-T has consistent wins in ASR accuracy, while CTC models excel at inference efficiency. Moreover, we selectively examine various modeling strategies for different training criteria, including modeling units, encoder architectures, pre-training, etc. Given such large-scale real-world streaming ASR application, to our best knowledge, we present the first comprehensive benchmark on these three widely used training criteria across a great many languages.

Supervised ASR models have reached unprecedented levels of accuracy, thanks in part to ever-increasing amounts of labelled training data. However, in many applications and locales, only moderate amounts of data are available, which has led to a surge in semi- and weakly-supervised learning research. In this paper, we conduct a large-scale study evaluating the effectiveness of weakly-supervised learning for speech recognition by using loosely related contextual information as a surrogate for ground-truth labels. For weakly supervised training, we use 50k hours of public English social media videos along with their respective titles and post text to train an encoder-decoder transformer model. Our best encoder-decoder models achieve an average of 20.8% WER reduction over a 1000 hours supervised baseline, and an average of 13.4% WER reduction when using only the weakly supervised encoder for CTC fine-tuning. Our results show that our setup for weak supervision improved both the encoder acoustic representations as well as the decoder language generation abilities.

Deep acoustic models typically receive features in the first layer of the network, and process increasingly abstract representations in the subsequent layers. Here, we propose to feed the input features at multiple depths in the acoustic model. As our motivation is to allow acoustic models to re-examine their input features in light of partial hypotheses we introduce intermediate model heads and loss function. We study this architecture in the context of deep Transformer networks, and we use an attention mechanism over both the previous layer activations and the input features. To train this model's intermediate output hypothesis, we apply the objective function at each layer right before feature re-use. We find that the use of such iterated loss significantly improves performance by itself, as well as enabling input feature re-use. We present results on both Librispeech, and a large scale video dataset, with relative improvements of 10 - 20% for Librispeech and 3.2 - 13% for videos.

We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to enable training deep transformers. We also present a preliminary study of using limited right context in transformer models, which makes it possible for streaming applications. We demonstrate that on the widely used Librispeech benchmark, our transformer-based AM outperforms the best published hybrid result by 19% to 26% relative when the standard n-gram language model (LM) is used. Combined with neural network LM for rescoring, our proposed approach achieves state-of-the-art results on Librispeech. Our findings are also confirmed on a much larger internal dataset.

Videos uploaded on social media are often accompanied with textual descriptions. In building automatic speech recognition (ASR) systems for videos, we can exploit the contextual information provided by such video metadata. In this paper, we explore ASR lattice rescoring by selectively attending to the video descriptions. We first use an attention based method to extract contextual vector representations of video metadata, and use these representations as part of the inputs to a neural language model during lattice rescoring. Secondly, we propose a hybrid pointer network approach to explicitly interpolate the word probabilities of the word occurrences in metadata. We perform experimental evaluations on both language modeling and ASR tasks, and demonstrate that both proposed methods provide performance improvements by selectively leveraging the video metadata.

Transformers, originally proposed for natural language processing (NLP) tasks, have recently achieved great success in automatic speech recognition (ASR). However, adjacent acoustic units (i.e., frames) are highly correlated, and long-distance dependencies between them are weak, unlike text units. It suggests that ASR will likely benefit from sparse and localized attention. In this paper, we propose Weak-Attention Suppression (WAS), a method that dynamically induces sparsity in attention probabilities. We demonstrate that WAS leads to consistent Word Error Rate (WER) improvement over strong transformer baselines. On the widely used LibriSpeech benchmark, our proposed method reduced WER by 10%$ on test-clean and 5% on test-other for streamable transformers, resulting in a new state-of-the-art among streaming models. Further analysis shows that WAS learns to suppress attention of non-critical and redundant continuous acoustic frames, and is more likely to suppress past frames rather than future ones. It indicates the importance of lookahead in attention-based ASR models.

Transformer-based acoustic modeling has achieved great success for both hybrid and sequence-to-sequence speech recognition.However, it requires access to the full sequence, and the computational cost grows quadratically with respect to the input sequence length.These factors limit its adoption for streaming applications.In this work, we proposed a novel augmented memory self-attention, which attends on a short segment of the input sequence and a bank of memories.The memory bank stores the embedding information for all the processed segments.On the librispeech benchmark, our proposed method outperforms all the existing streamable transformer methods by a large margin and achieved over 15% relative error reduction, compared with the widely used LC-BLSTM baseline.Our findings are also confirmed on some large internal datasets.

In this work, we first show that on the widely used LibriSpeech benchmark, our transformer-based context-dependent connectionist temporal classification (CTC) system produces state-ofthe-art results.We then show that using wordpieces as modeling units combined with CTC training, we can greatly simplify the engineering pipeline compared to conventional frame-based cross-entropy training by excluding all the GMM bootstrapping, decision tree building and force alignment steps, while still achieving very competitive word-error-rate.Additionally, using wordpieces as modeling units can significantly improve runtime efficiency since we can use larger stride without losing accuracy.We further confirm these findings on two internal VideoASR datasets: German, which is similar to English as a fusional language, and Turkish, which is an agglutinative language.