SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale
This work addresses the commercialization challenges of ASR for companies lacking extensive human and computational resources, though it is incremental as it builds on existing weak supervision and inference optimization techniques.
The paper tackles the problem of training and deploying end-to-end automatic speech recognition systems with limited labeled data and computational resources, achieving an 8% relative improvement in word-error rate and a 600% speedup compared to a third-party ASR system, while serving 12 million queries daily on a smart television.
End-to-end automatic speech recognition systems represent the state of the art, but they rely on thousands of hours of manually annotated speech for training, as well as heavyweight computation for inference. Of course, this impedes commercialization since most companies lack vast human and computational resources. In this paper, we explore training and deploying an ASR system in the label-scarce, compute-limited setting. To reduce human labor, we use a third-party ASR system as a weak supervision source, supplemented with labeling functions derived from implicit user feedback. To accelerate inference, we propose to route production-time queries across a pool of CUDA graphs of varying input lengths, the distribution of which best matches the traffic's. Compared to our third-party ASR, we achieve a relative improvement in word-error rate of 8% and a speedup of 600%. Our system, called SpeechNet, currently serves 12 million queries per day on our voice-enabled smart television. To our knowledge, this is the first time a large-scale, Wav2vec-based deployment has been described in the academic literature.