In this work, we investigate two popular end-to-end automatic speech recognition (ASR) models, namely Connectionist Temporal Classification (CTC) and RNN-Transducer (RNN-T), for offline recognition of voice search queries, with up to 2B model parameters. The encoders of our models use the neural architecture of Google's universal speech model (USM), with additional funnel pooling layers to significantly reduce the frame rate and speed up training and inference. We perform extensive studies on vocabulary size, time reduction strategy, and its generalization performance on long-form test sets. Despite the speculation that, as the model size increases, CTC can be as good as RNN-T which builds label dependency into the prediction, we observe that a 900M RNN-T clearly outperforms a 1.8B CTC and is more tolerant to severe time reduction, although the WER gap can be largely removed by LM shallow fusion.
Automatic speech recognition (ASR) systems have been shown to have large quality disparities between the language varieties they are intended or expected to recognize. One way to mitigate this is to train or fine-tune models with more representative datasets. But this approach can be hindered by limited in-domain data for training and evaluation. We propose a new way to improve the robustness of a US English short-form speech recognizer using a small amount of out-of-domain (long-form) African American English (AAE) data. We use CORAAL, YouTube and Mozilla Common Voice to train an audio classifier to approximately output whether an utterance is AAE or some other variety including Mainstream American English (MAE). By combining the classifier output with coarse geographic information, we can select a subset of utterances from a large corpus of untranscribed short-form queries for semi-supervised learning at scale. Fine-tuning on this data results in a 38.5% relative word error rate disparity reduction between AAE and MAE without reducing MAE quality.
RNN-T is currently considered the industry standard in ASR due to its exceptional WERs in various benchmark tests and its ability to support seamless streaming and longform transcription. However, its biggest drawback lies in the significant discrepancy between its training and inference objectives. During training, RNN-T maximizes all alignment probabilities by teacher forcing, while during inference, it uses beam search which may not necessarily find the maximum probable alignment. Additionally, RNN-T's inability to experience mistakes during teacher forcing training makes it more problematic when a mistake occurs in inference. To address this issue, this paper proposes a Reinforcement Learning method that minimizes the gap between training and inference time. Our Edit Distance based RL (EDRL) approach computes rewards based on the edit distance, and trains the network at every action level. The proposed approach yielded SoTA WERs on LibriSpeech for the 600M Conformer RNN-T model.
Speech data from different domains has distinct acoustic and linguistic characteristics. It is common to train a single multidomain model such as a Conformer transducer for speech recognition on a mixture of data from all domains. However, changing data in one domain or adding a new domain would require the multidomain model to be retrained. To this end, we propose a framework called modular domain adaptation (MDA) that enables a single model to process multidomain data while keeping all parameters domain-specific, i.e., each parameter is only trained by data from one domain. On a streaming Conformer transducer trained only on video caption data, experimental results show that an MDA-based model can reach similar performance as the multidomain model on other domains such as voice search and dictation by adding per-domain adapters and per-domain feed-forward networks in the Conformer encoder.
Foundation models (FMs), that are trained on broad data at scale and are adaptable to a wide range of downstream tasks, have brought large interest in the research community. Benefiting from the diverse data sources such as different modalities, languages and application domains, foundation models have demonstrated strong generalization and knowledge transfer capabilities. In this paper, we present a pioneering study towards building an efficient solution for FM-based speech recognition systems. We adopt the recently developed self-supervised BEST-RQ for pretraining, and propose the joint finetuning with both source and unsupervised target domain data using JUST Hydra. The FM encoder adapter and decoder are then finetuned to the target domain with a small amount of supervised in-domain data. On a large-scale YouTube and Voice Search task, our method is shown to be both data and model parameter efficient. It achieves the same quality with only 21.6M supervised in-domain data and 130.8M finetuned parameters, compared to the 731.1M model trained from scratch on additional 300M supervised in-domain data.
Self-supervised pre-training of a speech foundation model, followed by supervised fine-tuning, has shown impressive quality improvements on automatic speech recognition (ASR) tasks. Fine-tuning separate foundation models for many downstream tasks are expensive since the foundation model is usually very big. Parameter-efficient fine-tuning methods (e.g. adapter, sparse update methods) offer an alternative paradigm where a small set of parameters are updated to adapt the foundation model to new tasks. However, these methods still suffer from a high computational memory cost and slow training speed because they require backpropagation through the entire neural network at each step. In the paper, we analyze the performance of features at different layers of a foundation model on the speech recognition task and propose a novel hierarchical feature fusion method for resource-efficient transfer learning from speech foundation models. Experimental results show that the proposed method can achieve better performance on speech recognition task than existing algorithms with fewer number of trainable parameters, less computational memory cost and faster training speed. After combining with Adapters at all layers, the proposed method can achieve the same performance as fine-tuning the whole model with $97\%$ fewer trainable encoder parameters and $53\%$ faster training speed.
Knowledge distillation is an effective machine learning technique to transfer knowledge from a teacher model to a smaller student model, especially with unlabeled data. In this paper, we focus on knowledge distillation for the RNN-T model, which is widely used in state-of-the-art (SoTA) automatic speech recognition (ASR). Specifically, we compared using soft and hard target distillation to train large-scaleRNN-T models on the LibriSpeech/LibriLight public dataset (60k hours) and our in-house data (600k hours). We found that hard tar-gets are more effective when the teacher and student have different architecture, such as large teacher and small streaming student. On the other hand, soft target distillation works better in self-training scenario like iterative large teacher training. For a large model with0.6B weights, we achieve a new SoTA word error rate (WER) on LibriSpeech (8% relative improvement on dev-other) using Noisy Student Training with soft target distillation. It also allows our production teacher to adapt new data domain continuously.
In this paper, we propose a dynamic cascaded encoder Automatic Speech Recognition (ASR) model, which unifies models for different deployment scenarios. Moreover, the model can significantly reduce model size and power consumption without loss of quality. Namely, with the dynamic cascaded encoder model, we explore three techniques to maximally boost the performance of each model size: 1) Use separate decoders for each sub-model while sharing the encoders; 2) Use funnel-pooling to improve the encoder efficiency; 3) Balance the size of causal and non-causal encoders to improve quality and fit deployment constraints. Overall, the proposed large-medium model has 30% smaller size and reduces power consumption by 33%, compared to the baseline cascaded encoder model. The triple-size model that unifies the large, medium, and small models achieves 37% total size reduction with minimal quality loss, while substantially reducing the engineering efforts of having separate models.
State-of-the-art automatic speech recognition (ASR) systems are trained with tens of thousands of hours of labeled speech data. Human transcription is expensive and time consuming. Factors such as the quality and consistency of the transcription can greatly affect the performance of the ASR models trained with these data. In this paper, we show that we can train a strong teacher model to produce high quality pseudo labels by utilizing recent self-supervised and semi-supervised learning techniques. Specifically, we use JUST (Joint Unsupervised/Supervised Training) and iterative noisy student teacher training to train a 600 million parameter bi-directional teacher model. This model achieved 4.0% word error rate (WER) on a voice search task, 11.1% relatively better than a baseline. We further show that by using this strong teacher model to generate high-quality pseudo labels for training, we can achieve 13.6% relative WER reduction (5.9% to 5.1%) for a streaming model compared to using human labels.