Related papers: oboVox Far Field Speaker Recognition: A Novel Data…
We present the recent advances along with an error analysis of the IBM speaker recognition system for conversational speech. Some of the key advancements that contribute to our system include: a nearest-neighbor discriminant analysis (NDA)…
This paper aims to improve the widely used deep speaker embedding x-vector model. We propose the following improvements: (1) a hybrid neural network structure using both time delay neural network (TDNN) and long short-term memory neural…
Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…
In this paper, we propose an online speaker diarization system based on Relation Network, named RenoSD. Unlike conventional diariztion systems which consist of several independently-optimized modules, RenoSD implements…
This paper investigates a self-adaptation method for speech enhancement using auxiliary speaker-aware features; we extract a speaker representation used for adaptation directly from the test utterance. Conventional studies of deep neural…
Modern automatic speaker verification relies largely on deep neural networks (DNNs) trained on mel-frequency cepstral coefficient (MFCC) features. While there are alternative feature extraction methods based on phase, prosody and long-term…
DeepFake Audio, unlike DeepFake images and videos, has been relatively less explored from detection perspective, and the solutions which exist for the synthetic speech classification either use complex networks or dont generalize to…
The front-end module in multi-channel automatic speech recognition (ASR) systems mainly use microphone array techniques to produce enhanced signals in noisy conditions with reverberation and echos. Recently, neural network (NN) based…
This paper presents an end-to-end model designed to improve automatic speech recognition (ASR) for a particular speaker in a crowded, noisy environment. The model utilizes a single-channel speech enhancement module that isolates the…
Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…
Modern speaker verification models use deep neural networks to encode utterance audio into discriminative embedding vectors. During the training process, these networks are typically optimized to differentiate arbitrary speakers. This…
Speaker verification is to judge the similarity between two unknown voices in an open set, where the ideal speaker embedding should be able to condense discriminant information into a compact utterance-level representation that has small…
Although end-to-end automatic speech recognition (E2E ASR) has achieved great performance in tasks that have numerous paired data, it is still challenging to make E2E ASR robust against noisy and low-resource conditions. In this study, we…
Training speaker-discriminative and robust speaker verification systems without speaker labels is still challenging and worthwhile to explore. In this study, we propose an effective self-supervised learning framework and a novel…
Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy…
Research in speaker recognition has recently seen significant progress due to the application of neural network models and the availability of new large-scale datasets. There has been a plethora of work in search for more powerful…
Addressing the detrimental impact of non-stationary environmental noise on automatic speech recognition (ASR) has been a persistent and significant research focus. Despite advancements, this challenge continues to be a major concern.…
We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest…
Disordered speech recognition is a highly challenging task. The underlying neuro-motor conditions of people with speech disorders, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large…
Background noise reduces speech intelligibility and quality, making speaker verification (SV) in noisy environments a challenging task. To improve the noise robustness of SV systems, additive noise data augmentation method has been commonly…