A single speech encoder trained via ASR-aware distillation with variable attention masking performs competitively in both streaming and full-context modes at 200M and 2B scale.
Multi-mode Transformer Transducer with Stochastic Future Context
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Automatic speech recognition (ASR) models make fewer errors when more surrounding speech information is presented as context. Unfortunately, acquiring a larger future context leads to higher latency. There exists an inevitable trade-off between speed and accuracy. Naively, to fit different latency requirements, people have to store multiple models and pick the best one under the constraints. Instead, a more desirable approach is to have a single model that can dynamically adjust its latency based on different constraints, which we refer to as Multi-mode ASR. A Multi-mode ASR model can fulfill various latency requirements during inference -- when a larger latency becomes acceptable, the model can process longer future context to achieve higher accuracy and when a latency budget is not flexible, the model can be less dependent on future context but still achieve reliable accuracy. In pursuit of Multi-mode ASR, we propose Stochastic Future Context, a simple training procedure that samples one streaming configuration in each iteration. Through extensive experiments on AISHELL-1 and LibriSpeech datasets, we show that a Multi-mode ASR model rivals, if not surpasses, a set of competitive streaming baselines trained with different latency budgets.
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation
A single speech encoder trained via ASR-aware distillation with variable attention masking performs competitively in both streaming and full-context modes at 200M and 2B scale.