Learning Online Alignments with Continuous Rewards Policy Gradient
원문 초록
Sequence-to-sequence models with soft attention had significant success in machine translation, speech recognition, and question answering. Though capable and easy to use, they require that the entirety of the input sequence is available at the beginning of inference, an assumption that is not valid for instantaneous translation and speech recognition. To address this problem, we present a new method for solving sequence-to-sequence problems using hard online alignments instead of soft offline alignments. The online alignments model is able to start producing outputs without the need to first process the entire input sequence. A highly accurate online sequence-to-sequence model is useful because it can be used to build an accurate voice-based instantaneous translator. Our model uses hard binary stochastic decisions to select the timesteps at which outputs will be produced. The model is trained to produce these stochastic decisions using a standard policy gradient method. In our experiments, we show that this model achieves encouraging performance on TIMIT and Wall Street Journal (WSJ) speech recognition datasets.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
TASK AWARE MULTI-TASK LEARNING FOR SPEECH TO TEXT TASKS
HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation
First Steps Towards Voice Anonymization for Code-Switching Speech
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement
CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation
Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices
토론
이 논문과 연결된 포럼 글이 아직 없습니다.