Related papers: Speech2Phone: A Novel and Efficient Method for Tra…

A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences. Speaker adaptation techniques play a vital role to reduce the mismatch. Model-based…

This paper describes our RoyalFlush system for the track of multi-speaker automatic speech recognition (ASR) in the M2MeT challenge. We adopted the serialized output training (SOT) based multi-speakers ASR system with large-scale simulation…

In this study, we focus on Singing Voice Mean Opinion Score (SingMOS) prediction. Previous research have shown the performance benefit with the use of state-of-the-art (SOTA) pre-trained models (PTMs). However, they haven't explored speaker…

When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead. Many studies…

Traditional speech separation and speaker diarization approaches rely on prior knowledge of target speakers or a predetermined number of participants in audio signals. To address these limitations, recent advances focus on developing…

Audio-visual speech separation methods aim to integrate different modalities to generate high-quality separated speech, thereby enhancing the performance of downstream tasks such as speech recognition. Most existing state-of-the-art (SOTA)…

In this work, we propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition, which can \textbf{re-purpose} well-trained English automatic speech recognition (ASR) models to…

This paper proposes speaker-adaptive neural vocoders for parametric text-to-speech (TTS) systems. Recently proposed WaveNet-based neural vocoding systems successfully generate a time sequence of speech signal with an autoregressive…

We introduce and analyze a novel approach to the problem of speaker identification in multi-party recorded meetings. Given a speech segment and a set of available candidate profiles, we propose a novel data-driven way to model the distance…

Speech modeling methods learn one embedding for a fixed segment of speech, typically in between 10-25 ms. The information present in speech can be divided into two categories: "what is being said" (content) and "how it is expressed" (other)…

This paper studies the task of speech reconstruction from ultrasound tongue images and optical lip videos recorded in a silent speaking mode, where people only activate their intra-oral and extra-oral articulators without producing sound.…

Speech-based analysis offers a scalable and non-invasive approach for detecting cognitive decline, yet progress has been constrained by the limited availability of clinically validated datasets collected under realistic conditions. We…

Many recent studies have focused on fine-tuning pre-trained models for speech emotion recognition (SER), resulting in promising performance compared to traditional methods that rely largely on low-level, knowledge-inspired acoustic…

Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-to-end SLU systems map speech directly to intent through a single trainable model. Achieving high accuracy with these…

This paper presents a description of STC Ltd. systems submitted to the NIST 2021 Speaker Recognition Evaluation for both fixed and open training conditions. These systems consists of a number of diverse subsystems based on using deep neural…

Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find shortcuts such as speaker characteristics. These shortcuts…

Traditional vocoder-based statistical parametric speech synthesis can be advantageous in applications that require low computational complexity. Recent neural vocoders, which can produce high naturalness, still cannot fulfill the…

In the traditional cascading architecture for spoken language understanding (SLU), it has been observed that automatic speech recognition errors could be detrimental to the performance of natural language understanding. End-to-end (E2E) SLU…

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…

In this study, we address the challenge of speaker recognition using a novel data augmentation technique of adding noise to enrollment files. This technique efficiently aligns the sources of test and enrollment files, enhancing…