Related papers: Globally Normalising the Transducer for Streaming …

Improving model's generalizability against domain shifts is crucial, especially for safety-critical applications such as autonomous driving. Real-world domain styles can vary substantially due to environment changes and sensor noises, but…

This paper improves the streaming transformer transducer for speech recognition by using non-causal convolution. Many works apply the causal convolution to improve streaming transformer ignoring the lookahead context. We propose to use…

Streaming recognition and segmentation of multi-party conversations with overlapping speech is crucial for the next generation of voice assistant applications. In this work we address its challenges discovered in the previous work on…

We propose to deliberate the hypothesis alignment of a streaming RNN-T model with the previously proposed Align-Refine non-autoregressive decoding method and its improved versions. The method performs a few refinement steps, where each step…

Recent advances of end-to-end models have outperformed conventional models through employing a two-pass model. The two-pass model provides better speed-quality trade-offs for on-device speech recognition, where a 1st-pass model generates…

While recurrent neural networks still largely define state-of-the-art speech recognition systems, the Transformer network has been proven to be a competitive alternative, especially in the offline condition. Most studies with Transformers…

We investigate a set of techniques for RNN Transducers (RNN-Ts) that were instrumental in lowering the word error rate on three different tasks (Switchboard 300 hours, conversational Spanish 780 hours and conversational Italian 900 hours).…

In recent years, all-neural end-to-end approaches have obtained state-of-the-art results on several challenging automatic speech recognition (ASR) tasks. However, most existing works focus on building ASR models where train and test data…

This paper proposes a modification to RNN-Transducer (RNN-T) models for automatic speech recognition (ASR). In standard RNN-T, the emission of a blank symbol consumes exactly one input frame; in our proposed method, we introduce additional…

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

We systematically explored a spectrum of normalization algorithms related to Batch Normalization (BN) and propose a generalized formulation that simultaneously solves two major limitations of BN: (1) online learning and (2) recurrent…

The attention-based Transformer model has achieved promising results for speech recognition (SR) in the offline mode. However, in the streaming mode, the Transformer model usually incurs significant latency to maintain its recognition…

Zero-shot streaming text-to-speech is an important research topic in human-computer interaction. Existing methods primarily use a lookahead mechanism, relying on future text to achieve natural streaming speech synthesis, which introduces…

Recent research shows end-to-end ASR systems can recognize overlapped speech from multiple speakers. However, all published works have assumed no latency constraints during inference, which does not hold for most voice assistant…

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. However, emitting fast without degrading quality, as measured by word error rate (WER), is highly challenging. Existing…

End-to-end models are favored in automatic speech recognition (ASR) because of its simplified system structure and superior performance. Among these models, recurrent neural network transducer (RNN-T) has achieved significant progress in…

In this paper, we present a novel training method for speaker change detection models. Speaker change detection is often viewed as a binary sequence labelling problem. The main challenges with this approach are the vagueness of annotated…

Graph neural networks (GNNs) have achieved strong performance in various applications. In the real world, network data is usually formed in a streaming fashion. The distributions of patterns that refer to neighborhood information of nodes…

In this paper, several works are proposed to address practical challenges for deploying RNN Transducer (RNN-T) based speech recognition system. These challenges are adapting a well-trained RNN-T model to a new domain without collecting the…

Target-speaker speech recognition aims to recognize target-speaker speech from noisy environments with background noise and interfering speakers. This work presents a joint framework that combines time-domain target-speaker speech…