We propose a massively multilingual speech-to-text neural forced aligner that supports 98 languages with a single architecture. The aligner takes self-supervised discrete acoustic units and unnormalized characters including punctuation marks as inputs. We train the aligner as a part of a non-autoregressive text-to-unit (T2U) model without any external aligner. The T2U model is trained on speech-text paired data in various domains and recording conditions. Experimental evaluation demonstrates that the proposed T2U aligner achieves competitive quality to existing monolingual aligners while supporting much more languages. We also showcase a zero-shot forced alignment capability on unseen languages.

Expanding the language coverage of speech technology has the potential to improve access to information for many more people. However, current speech technology is restricted to about one hundred languages which is a small fraction of the over 7,000 languages spoken around the world. The Massively Multilingual Speech (MMS) project increases the number of supported languages by 10-40x, depending on the task while providing improved accuracy compared to prior work. The main ingredients are a new dataset based on readings of publicly available religious texts and effectively leveraging self-supervised learning. We built pre-trained wav2vec 2.0 models covering 1,406 languages, a single multilingual automatic speech recognition model for 1,107 languages, speech synthesis models for the same number of languages, as well as a language identification model for 4,017 languages. Experiments show that our multilingual speech recognition model more than halves the word error rate of Whisper on 54 languages of the FLEURS benchmark while being trained on a small fraction of the labeled data.

Yun Tang, Anna Sun, Hirofumi Inaguma, Xinyue Chen, Ning Dong, Xutai Ma, Paden Tomasello, Juan Pino. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Automatic speech recognition research focuses on training and evaluating on static datasets. Yet, as speech models are increasingly deployed on personal devices, such models encounter user-specific distributional shifts. To simulate this real-world scenario, we introduce LibriContinual, a continual learning benchmark for speaker-specific domain adaptation derived from LibriVox audiobooks, with data corresponding to 118 individual speakers and 6 train splits per speaker of different sizes. Additionally, current speech recognition models and continual learning algorithms are not optimized to be compute-efficient. We adapt a general-purpose training algorithm NetAug for ASR and create a novel Conformer variant called the DisConformer (Disentangled Conformer). This algorithm produces ASR models consisting of a frozen ‘core’ network for general-purpose use and several tunable ‘augment’ networks for speaker-specific tuning. Using such models, we propose a novel compute-efficient continual learning algorithm called DisentangledCL. Our experiments show that the DisConformer models significantly outperform base-lines on general ASR i.e. LibriSpeech (15.58% rel. WER on test-other). On speaker-specific LibriContinual they significantly outper-form trainable-parameter-matched baselines (by 20.65% rel. WER on test) and even match fully finetuned baselines in some settings.

The research community has produced many successful self-supervised speech representation learning methods over the past few years. Discrete units have been utilized in various self-supervised learning frameworks, such as VQ-VAE [1], wav2vec 2.0 [2], Hu-BERT [3], and Wav2Seq [4]. This paper studies the impact of altering the granularity and improving the quality of these discrete acoustic units for pre-training encoder-only and encoder-decoder models. We systematically study the current proposals of using Byte-Pair Encoding (BPE) and new extensions that use cluster smoothing and Brown clustering. The quality of learned units is studied intrinsically using zero speech metrics and on the down-stream speech recognition (ASR) task. Our results suggest that longer-range units are helpful for encoder-decoder pre-training; however, encoder-only masked-prediction models cannot yet benefit from self-supervised word-like targets.

Spoken language understanding (SLU) is a important field between the Speech and NLP community focused on converting a users’ speech utterance into an executable semantic parse. In order to facilitate open research in this space, we introduce the 1st Spoken Language Understanding challenge hosted at ICASSP 2023. We leverage the newly released SLU dataset STOP [1]. In this challenge, participants are asked to compete in 3 tracks of SLU relevant to the field (1) Quality: build the highest performance model (2) On-device: build the highest quality model under 15M parameters and (3) Low-resource: Achieve the highest quality in a low-resource setting. While participants have made significant strides in the challenge, there is still a long way to go in building data and compute efficient SLU models.

Abstract We introduce dGSLM, the first “textless” model able to generate audio samples of naturalistic spoken dialogues. It uses recent work on unsupervised spoken unit discovery coupled with a dual-tower transformer architecture with cross-attention trained on 2000 hours of two-channel raw conversational audio (Fisher dataset) without any text or labels. We show that our model is able to generate speech, laughter, and other paralinguistic signals in the two channels simultaneously and reproduces more naturalistic and fluid turn taking compared to a text-based cascaded model.1,2

As the computational requirements for machine learning systems and the size and complexity of machine learning frameworks increases, essential framework innovation has become challenging. While computational needs have driven recent compiler, networking, and hardware advancements, utilization of those advancements by machine learning tools is occurring at a slower pace. This is in part due to the difficulties involved in prototyping new computational paradigms with existing frameworks. Large frameworks prioritize machine learning researchers and practitioners as end users and pay comparatively little attention to systems researchers who can push frameworks forward — we argue that both are equally important stakeholders. We introduce Flashlight, an open-source library built to spur innovation in machine learning tools and systems by prioritizing open, modular, customizable internals and state-of-the-art, research-ready models and training setups across a variety of domains. Flashlight allows systems researchers to rapidly prototype and experiment with novel ideas in machine learning computation and has low overhead, competing with and often outperforming other popular machine learning frameworks. We see Flashlight as a tool enabling research that can benefit widely used libraries downstream and bring machine learning and systems researchers closer together.

We propose a novel deliberation-based approach to end-to-end (E2E) spoken language understanding (SLU), where a streaming automatic speech recognition (ASR) model produces the first-pass hypothesis and a second-pass natural language understanding (NLU) component generates the semantic parse by conditioning on both ASR's text and audio embeddings.By formulating E2E SLU as a generalized decoder, our system is able to support complex compositional semantic structures.Furthermore, the sharing of parameters between ASR and NLU makes the system especially suitable for resource-constrained (on-device) environments; our proposed approach consistently outperforms strong pipeline NLU baselines by 0.60% to 0.65% on the spoken version of the TOPv2 dataset (STOP).We demonstrate that the fusion of text and audio features, coupled with the system's ability to rewrite the first-pass hypothesis, makes our approach more robust to ASR errors.Finally, we show that our approach can significantly reduce the degradation when moving from natural speech to synthetic speech training, but more work is required to make text-to-speech (TTS) a viable solution for scaling up E2E SLU.

End-to-end spoken language understanding (SLU) predicts intent directly from audio using a single model. It promises to improve the performance of assistant systems by leveraging acoustic information lost in the intermediate textual representation and preventing cascading errors from Automatic Speech Recognition (ASR). Further, having one unified model has efficiency advantages when deploying assistant systems on-device. However, the limited number of public audio datasets with semantic parse labels hinders the research progress in this area. In this paper, we release the Spoken Task-Oriented semantic Parsing (STOP) dataset1, the largest and most complex SLU dataset publicly available. Additionally, we define low-resource splits to establish a benchmark for improving SLU when limited labeled data is available. Furthermore, in addition to the human-recorded audio, we are releasing a TTS-generated versions to benchmark the performance for low-resource and domain adaptation of end-to-end SLU systems.

Self-training and unsupervised pre-training have emerged as effective approaches to improve speech recognition systems using unlabeled data. However, it is not clear whether they learn similar patterns or if they can be effectively combined. In this paper, we show that pseudo-labeling and pre-training with wav2vec 2.0 are complementary in a variety of labeled data setups. Using just 10 minutes of labeled data from Libri-light as well as 53k hours of unlabeled data from LibriVox achieves word error rates (WER) of 2.8%/4.8% on the clean and other test sets of Librispeech – rivaling the best published systems trained on 960 hours of labeled data only a year ago. Training on all labeled data of Librispeech achieves WERs of 1.5%/3.1%.

Is pushing numbers on a single benchmark valuable in automatic speech recognition? Research results in acoustic modeling are typically evaluated based on performance on a single dataset. While the research community has coalesced around various benchmarks, we set out to understand generalization performance in acoustic modeling across datasets - in particular, if models trained on a single dataset transfer to other (possibly out-of-domain) datasets. We show that, in general, reverberative and additive noise augmentation improves generalization performance across domains. Further, we demonstrate that when a large enough set of benchmarks is used, average word error rate (WER) performance over them provides a good proxy for performance on real-world noisy data. Finally, we show that training a single acoustic model on the most widely-used datasets - combined - reaches competitive performance on both research and real-world benchmarks.

We study training a single acoustic model for multiple languages with the aim of improving automatic speech recognition (ASR) performance on low-resource languages, and over-all simplifying deployment of ASR systems that support diverse languages. We perform an extensive benchmark on 51 languages, with varying amount of training data by language(from 100 hours to 1100 hours). We compare three variants of multilingual training from a single joint model without knowing the input language, to using this information, to multiple heads (one per language cluster). We show that multilingual training of ASR models on several languages can improve recognition performance, in particular, on low resource languages. We see 20.9%, 23% and 28.8% average WER relative reduction compared to monolingual baselines on joint model, joint model with language input and multi head model respectively. To our knowledge, this is the first work studying multilingual ASR at massive scale, with more than 50 languages and more than 16,000 hours of audio across them.