With the rise of short videos, the demand for selecting appropriate background music (BGM)
for a video has increased significantly, video-music retrieval (VMR) task gradually draws …

In this paper, we present TrimTail, a simple but effective emission regularization method to
improve the latency of streaming ASR models. The core idea of TrimTail is to apply length …

The CTC model has been widely applied to many application scenarios because of its
simple structure, excellent performance, and fast inference speed. There are many peaks in …

Connectionist Temporal Classification (CTC) suffers from the latency problem when applied
to streaming models. We argue that in CTC lattice, the alignments that can access more …

Connectionist temporal classification (CTC) models are known to have peaky output
distributions. Such behavior is not a problem for automatic speech recognition (ASR), but it …

This paper introduces a novel training framework called Focused Discriminative Training
(FDT) to further improve streaming word-piece end-to-end (E2E) automatic speech …

Multi-talker speech recognition (MTASR) faces unique challenges in disentangling and
transcribing overlapping speech. To address these challenges, this paper investigates the …

Automatic speech recognition (ASR) based on transducers is widely used. In training, a
transducer maximizes the summed posteriors of all paths. The path with the highest …

Transformer encoder with connectionist temporal classification (CTC) framework is widely
used for automatic speech recognition (ASR). However, knowledge distillation (KD) for ASR …

Modern systems for automatic speech recognition, including the RNN-Transducer and
Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required …