Related papers: Weakly-supervised forced alignment of disfluent sp…

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond transcription to produce richer outputs. Among these, word-level timestamp prediction is…

For end-to-end Automatic Speech Recognition (ASR) models, recognizing personal or rare phrases can be hard. A promising way to improve accuracy is through spelling correction (or rewriting) of the ASR lattice, where potentially…

This paper proposes a novel label-synchronous speech-to-text alignment technique for automatic speech recognition (ASR). The speech-to-text alignment is a problem of splitting long audio recordings with un-aligned transcripts into…

This paper proposes an extremely lightweight phone-based transducer model with a tiny decoding graph on edge devices. First, a phone synchronous decoding (PSD) algorithm based on blank label skipping is first used to speed up the transducer…

We consider the task of unsupervised extraction of meaningful latent representations of speech by applying autoencoding neural networks to speech waveforms. The goal is to learn a representation able to capture high level semantic content…

The optimization of a wavelet-based algorithm to improve speech intelligibility along with the full data set and results are reported. The discrete-time speech signal is split into frequency sub-bands via a multi-level discrete wavelet…

Despite rapid advancement in recent years, current speech enhancement models often produce speech that differs in perceptual quality from real clean speech. We propose a learning objective that formalizes differences in perceptual quality,…

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…

Supervised ASR models have reached unprecedented levels of accuracy, thanks in part to ever-increasing amounts of labelled training data. However, in many applications and locales, only moderate amounts of data are available, which has led…

Detecting medical conditions from speech acoustics is fundamentally a weakly-supervised learning problem: a single, often noisy, session-level label must be linked to nuanced patterns within a long, complex audio recording. This task is…

Reducing prediction delay for streaming end-to-end ASR models with minimal performance regression is a challenging problem. Constrained alignment is a well-known existing approach that penalizes predicted word boundaries using external…

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…

Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the…

The recurrent neural network transducer (RNN-T) objective plays a major role in building today's best automatic speech recognition (ASR) systems for production. Similarly to the connectionist temporal classification (CTC) objective, the…

Building multilingual and crosslingual models help bring different languages together in a language universal space. It allows models to share parameters and transfer knowledge across languages, enabling faster and better adaptation to a…

A large number of works view the automatic assessment of speech from an utterance- or system-level perspective. While such approaches are good in judging overall quality, they cannot adequately explain why a certain score was assigned to an…

To train transcriptor models that produce robust results, a large and diverse labeled dataset is required. Finding such data with the necessary characteristics is a challenging task, especially for languages less popular than English.…

Recently, flow matching based speech synthesis has significantly enhanced the quality of synthesized speech while reducing the number of inference steps. In this paper, we introduce SlimSpeech, a lightweight and efficient speech synthesis…

Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping…