Related papers: CTC-based Compression for Direct Speech Translatio…

Connectionist temporal classification (CTC) -based models are attractive in automatic speech recognition (ASR) because of their non-autoregressive nature. To take advantage of text-only data, language model (LM) integration approaches such…

This paper proposes a direct text to speech translation system using discrete acoustic units. This framework employs text in different source languages as input to generate speech in the target language without the need for text…

Synthesized speech is common today due to the prevalence of virtual assistants, easy-to-use tools for generating and modifying speech signals, and remote work practices. Synthesized speech can also be used for nefarious purposes, including…

We present STFTCodec, a novel spectral-based neural audio codec that efficiently compresses audio using Short-Time Fourier Transform (STFT). Unlike waveform-based approaches that require large model capacity and substantial memory…

This paper presents a new neural speech compression method that is practical in the sense that it operates at low bitrate, introduces a low latency, is compatible in computational complexity with current mobile devices, and provides a…

Long Short Term Memory Connectionist Temporal Classification (LSTM-CTC) based end-to-end models are widely used in speech recognition due to its simplicity in training and efficiency in decoding. In conventional LSTM-CTC based models, a…

This paper presents a method for modeling optical dynamic range compressors using deep neural networks with Selective State Space models. The proposed approach surpasses previous methods based on recurrent layers by employing a Selective…

Scaling language models to longer contexts is essential for capturing rich dependencies across extended discourse. However, na\"ive context extension imposes significant computational and memory burdens, often resulting in inefficiencies…

The goal of accent conversion (AC) is to convert speech accents while preserving content and speaker identity. Previous methods either required reference utterances during inference, did not preserve speaker identity well, or used…

A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps the transformation between source speech and target text. Such modeling suffers…

Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question.…

We propose a CTC alignment-based single step non-autoregressive transformer (CASS-NAT) for speech recognition. Specifically, the CTC alignment contains the information of (a) the number of tokens for decoder input, and (b) the time span of…

In this paper, we propose a simple but effective method to decode the output of Connectionist Temporal Classifier (CTC) model using a bi-directional neural language model. The bidirectional language model uses the future as well as the past…

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…

This paper works on non-autoregressive automatic speech recognition. A unimodal aggregation (UMA) is proposed to segment and integrate the feature frames that belong to the same text token, and thus to learn better feature representations…

The acoustic-to-word model based on the Connectionist Temporal Classification (CTC) criterion is a natural end-to-end (E2E) system directly targeting word as output unit. Two issues exist in the system: first, the current output of the CTC…

Recently, the advance in deep learning has brought a considerable improvement in the end-to-end speech recognition field, simplifying the traditional pipeline while producing promising results. Among the end-to-end models, the connectionist…

Most existing sequence labelling models rely on a fixed decomposition of a target sequence into a sequence of basic units. These methods suffer from two major drawbacks: 1) the set of basic units is fixed, such as the set of words,…

State-of-the-art Transformer-based neural machine translation (NMT) systems still follow a standard encoder-decoder framework, in which source sentence representation can be well done by an encoder with self-attention mechanism. Though…

There has been an increasing interest in large speech models that can perform multiple tasks in a single model. Such models usually adopt an encoder-decoder or decoder-only architecture due to their popularity and good performance in many…