Layer Reduction: Accelerating Conformer-Based Self-Supervised Model via Layer Consistency
Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. However, both the training and inference process of these models may encounter prohibitively high computational cost and large parameter budget. Although Parameter Sharing Strategy (PSS) proposed in ALBERT paves the way for parameter reduction, the computation required remains the same. Interestingly, we found in experiments that distributions of feature embeddings from different Transformer layers are similar when PSS is integrated: a property termed as Layer Consistency (LC) in this paper. Given this similarity of feature distributions, we assume that feature embeddings from different layers would have similar representing power. In this work, Layer Consistency enables us to adopt Transformer-based models in a more efficient manner: the number of Conformer layers in each training iteration could be uniformly sampled and Shallow Layer Inference (SLI) could be applied to reduce the number of layers in inference stage. In experiments, our models are trained with LibriSpeech dataset and then evaluated on both phone classification and Speech Recognition tasks. We experimentally achieve 7.8X parameter reduction, 41.9% training speedup and 37.7% inference speedup while maintaining comparable performance with conventional BERT-like self-supervised methods.
Code (0)
등록된 구현이 없습니다.
Tasks
speech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Generalizing RNN-Transducer to Out-Domain Audio via Sparse Self-Attention Layers
Recurrent neural network transducer (RNN-T) is an end-to-end speech recognition framework converting input acoustic frames into a character sequence. The state-of-the-art encoder network for RNN-T is the Conformer, which…
speech-recognitionSpeech RecognitionAccidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models
In this paper, we extend previous self-supervised approaches for language identification by experimenting with Conformer based architecture in a multilingual pre-training paradigm. We find that pre-trained speech models …
Language IdentificationSpoken language identificationUconv-Conformer: High Reduction of Input Sequence Length for End-to-End Speech Recognition
Optimization of modern ASR architectures is among the highest priority tasks since it saves many computational resources for model training and inference. The work proposes a new Uconv-Conformer architecture based on the…
CPUGPUspeech-recognitionSpeech RecognitionEnd-to-end Neural Diarization: From Transformer to Conformer
We propose a new end-to-end neural diarization (EEND) system that is based on Conformer, a recently proposed neural architecture that combines convolutional mappings and Transformer to model both local and global depende…
Data AugmentationAdaptive Dropout for Pruning Conformers
This paper proposes a method to effectively perform joint training-and-pruning based on adaptive dropout layers with unit-wise retention probabilities. The proposed method is based on the estimation of a unit-wise retent…
speech-recognitionSpeech Recognition