Related papers: Exploring Pre-training with Alignments for RNN Tra…
Unification of automatic speech recognition (ASR) systems reduces development and maintenance costs, but training a single model to perform well in both offline and low-latency streaming settings remains challenging. We present a Unified…
We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS architecture in order to limit the future context and hence…
In streaming settings, speech recognition models have to map sub-sequences of speech to text before the full audio stream becomes available. However, since alignment information between speech and text is rarely available during training,…
End-to-end multilingual speech recognition models handle multiple languages through a single model, often incorporating language identification to automatically detect the language of incoming speech. Since the common scenario is where the…
Speech self-supervised pre-training can effectively improve the performance of downstream tasks. However, previous self-supervised learning (SSL) methods for speech, such as HuBERT and BEST-RQ, focus on utilizing non-causal encoders with…
Neural Machine Translation model is a sequence-to-sequence converter based on neural networks. Existing models use recurrent neural networks to construct both the encoder and decoder modules. In alternative research, the recurrent networks…
Punctuated text prediction is crucial for automatic speech recognition as it enhances readability and impacts downstream natural language processing tasks. In streaming scenarios, the ability to predict punctuation in real-time is…
RNN-Transducer has been one of promising architectures for end-to-end automatic speech recognition. Although RNN-Transducer has many advantages including its strong accuracy and streaming-friendly property, its high memory consumption…
While end-to-end ASR systems have proven competitive with the conventional hybrid approach, they are prone to accuracy degradation when it comes to noisy and low-resource conditions. In this paper, we argue that, even in such difficult…
Casual conversations involving multiple speakers and noises from surrounding devices are common in everyday environments, which degrades the performances of automatic speech recognition systems. These challenging characteristics of…
We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…
Neural transducers have been widely used in automatic speech recognition (ASR). In this paper, we introduce it to streaming end-to-end speech translation (ST), which aims to convert audio signals to texts in other languages directly.…
In this paper, we propose a context-aware keyword spotting model employing a character-level recurrent neural network (RNN) for spoken term detection in continuous speech. The RNN is end-to-end trained with connectionist temporal…
Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum, via a naive convolution…
While most deployed speech recognition systems today still run on servers, we are in the midst of a transition towards deployments on edge devices. This leap to the edge is powered by the progression from traditional speech recognition…
Automatic recognition systems for child speech are lagging behind those dedicated to adult speech in the race of performance. This phenomenon is due to the high acoustic and linguistic variability present in child speech caused by their…
As one of the most popular sequence-to-sequence modeling approaches for speech recognition, the RNN-Transducer has achieved evolving performance with more and more sophisticated neural network models of growing size and increasing training…
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…
In this paper, we propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We adapted the FastConformer architecture for streaming applications through: (1) constraining both the…
This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our…