Related papers: End-to-End Text-Dependent Speaker Verification

Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from…

We propose an approach to extract speaker embeddings that are robust to speaking style variations in text-independent speaker verification. Typically, speaker embedding extraction includes training a DNN for speaker classification and using…

This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language transcription during learning or decoding. We propose a model for direct speech-to-text translation, which…

Streaming multi-talker speech translation is a task that involves not only generating accurate and fluent translations with low latency but also recognizing when a speaker change occurs and what the speaker's gender is. Speaker change…

In this paper, we propose an online speaker adaptation method for WaveNet-based neural vocoders in order to improve their performance on speaker-independent waveform generation. In this method, a speaker encoder is first constructed using a…

The popularization of science can often be disregarded by scientists as it may be challenging to put highly sophisticated research into words that general public can understand. This work aims to help presenting speaker recognition research…

The number of end-to-end speech recognition models grows every year. These models are often adapted to new domains or languages resulting in a proliferation of expert systems that achieve great results on target data, while generally…

Recent advancements in scene text spotting have focused on end-to-end methodologies that heavily rely on precise location annotations, which are often costly and labor-intensive to procure. In this study, we introduce an innovative approach…

In this paper, we propose a quality-aware end-to-end audio-visual neural speaker diarization framework, which comprises three key techniques. First, our audio-visual model takes both audio and visual features as inputs, utilizing a series…

Speaker anonymization aims to conceal cues to speaker identity while preserving linguistic content. Current machine learning based approaches require substantial computational resources, hindering real-time streaming applications. To…

Overlapping speech diarization has been traditionally treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding multiple binary labels into a single label with…

The lack of speech data annotated with labels required for spoken language understanding (SLU) is often a major hurdle in building end-to-end (E2E) systems that can directly process speech inputs. In contrast, large amounts of text data…

The most common approach to speaker diarization is clustering of speaker embeddings. However, the clustering-based approach has a number of problems; i.e., (i) it is not optimized to minimize diarization errors directly, (ii) it cannot…

Thanks to recent advances in deep learning, sophisticated generation tools exist, nowadays, that produce extremely realistic synthetic speech. However, malicious uses of such tools are possible and likely, posing a serious threat to our…

We study multi-task learning for two orthogonal speech technology tasks: speech and speaker recognition. We use wav2vec2 as a base architecture with two task-specific output heads. We experiment with different architectural decisions to mix…

In practical settings, a speaker recognition system needs to identify a speaker given a short utterance, while the enrollment utterance may be relatively long. However, existing speaker recognition models perform poorly with such short…

Speech recognisers usually perform optimally only in a specific environment and need to be adapted to work well in another. For adaptation to a new speaker, there is often too little data for fine-tuning to be robust, and that data is…

Recent advancements in Self-Supervised Learning (SSL) have shown promising results in Speaker Verification (SV). However, narrowing the performance gap with supervised systems remains an ongoing challenge. Several studies have observed that…

The existing fake audio detection systems often rely on expert experience to design the acoustic features or manually design the hyperparameters of the network structure. However, artificial adjustment of the parameters can have a…

Automatic speaker verification, like every other biometric system, is vulnerable to spoofing attacks. Using only a few minutes of recorded voice of a genuine client of a speaker verification system, attackers can develop a variety of…