Related papers: Embeddings for DNN speaker adaptive training

Deep speaker embeddings have shown promising results in speaker recognition, as well as in other speaker-related tasks. However, some issues are still under explored, for instance, the information encoded in these representations and their…

LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify…

Though significant progress has been made for the voice conversion (VC) of typical speech, VC for atypical speech, e.g., dysarthric and second-language (L2) speech, remains a challenge, since it involves correcting for atypical prosody…

Speech emotion recognition (SER) has attracted great attention in recent years due to the high demand for emotionally intelligent speech interfaces. Deriving speaker-invariant representations for speech emotion recognition is crucial. In…

Significant progress has recently been made in speaker diarisation after the introduction of d-vectors as speaker embeddings extracted from neural network (NN) speaker classifiers for clustering speech segments. To extract better-performing…

Speech-driven visual speech synthesis involves mapping features extracted from acoustic speech to the corresponding lip animation controls for a face model. This mapping can take many forms, but a powerful approach is to use deep neural…

Automated speaker identification (SID) is a crucial step for the personalization of a wide range of speech-enabled services. Typical SID systems use a symmetric enrollment-verification framework with a single model to derive embeddings both…

We present a deep neural network (DNN) acoustic model that includes parametrised and differentiable pooling operators. Unsupervised acoustic model adaptation is cast as the problem of updating the decision boundaries implemented by each…

This paper presents a speech intelligibility model based on automatic speech recognition (ASR), combining phoneme probabilities from deep neural networks (DNN) and a performance measure that estimates the word error rate from these…

Dysarthric speech recognition (DSR) presents a formidable challenge due to inherent inter-speaker variability, leading to severe performance degradation when applying DSR models to new dysarthric speakers. Traditional speaker adaptation…

Estimating noise information exactly is crucial for noise aware training in speech applications including speech enhancement (SE) which is our focus in this paper. To estimate noise-only frames, we employ voice activity detection (VAD) to…

In general, the performance of automatic speech recognition (ASR) systems is significantly degraded due to the mismatch between training and test environments. Recently, a deep-learning-based image-to-image translation technique to…

Deep neural network (DNN)-based speech enhancement algorithms in microphone arrays have now proven to be efficient solutions to speech understanding and speech recognition in noisy environments. However, in the context of ad-hoc microphone…

Sentence embeddings enable us to capture the semantic similarity of short texts. Most sentence embedding models are trained for general semantic textual similarity tasks. Therefore, to use sentence embeddings in a particular domain, the…

Even though deep speaker models have demonstrated impressive accuracy in speaker verification tasks, this often comes at the expense of increased model size and computation time, presenting challenges for deployment in resource-constrained…

Recently, more and more zero-shot voice conversion algorithms have been proposed. As a fundamental part of zero-shot voice conversion, speaker embeddings are the key to improving the converted speech's speaker similarity. In this paper, we…

Performance degradation caused by language mismatch is a common problem when applying a speaker verification system on speech data in different languages. This paper proposes a domain transfer network, named EDITnet, to alleviate the…

This research addresses the problem of acoustic modeling of low-resource languages for which transcribed training data is absent. The goal is to learn robust frame-level feature representations that can be used to identify and distinguish…

Single channel target speaker separation (TSS) aims at extracting a speaker's voice from a mixture of multiple talkers given an enrollment utterance of that speaker. A typical deep learning TSS framework consists of an upstream model that…

In this paper, we propose a semi-supervised learning (SSL) technique for training deep neural networks (DNNs) to generate speaker-discriminative acoustic embeddings (speaker embeddings). Obtaining large amounts of speaker recognition…