Related papers: Deep Segment Attentive Embedding for Duration Robu…

Recent work has begun exploring neural acoustic word embeddings---fixed-dimensional vector representations of arbitrary-length speech segments corresponding to words. Such embeddings are applicable to speech retrieval and recognition tasks,…

Learning robust speaker representations under noisy conditions presents significant challenges, which requires careful handling of both discriminative and noise-invariant properties. In this work, we proposed an anchor-based stage-wise…

A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as feature extractors for speaker verification has shown…

In this paper we present a new method for text-independent speaker verification that combines segmental dynamic time warping (SDTW) and the d-vector approach. The d-vectors, generated from a feed forward deep neural network trained to…

Deep speaker embeddings have become the leading method for encoding speaker identity in speaker recognition tasks. The embedding space should ideally capture the variations between all possible speakers, encoding the multiple acoustic…

Lipreading, i.e. speech recognition from visual-only recordings of a speaker's face, can be achieved with a processing pipeline based solely on neural networks, yielding significantly better accuracy than conventional methods. Feed-forward…

Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on…

In multi-speaker applications is common to have pre-computed models from enrolled speakers. Using these models to identify the instances in which these speakers intervene in a recording is the task of speaker tracking. In this paper, we…

The adoption of advanced deep learning architectures in stuttering detection (SD) tasks is challenging due to the limited size of the available datasets. To this end, this work introduces the application of speech embeddings extracted from…

A number of studies have successfully developed speaker verification or presentation attack detection systems. However, studies integrating the two tasks remain in the preliminary stages. In this paper, we propose two approaches for…

The state-of-art approach to speaker verification involves the extraction of discriminative embeddings like x-vectors followed by a generative model back-end using a probabilistic linear discriminant analysis (PLDA). In this paper, we…

Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective for word…

Recent studies have shown that frame-level deep speaker features can be derived from a deep neural network with the training target set to discriminate speakers by a short speech segment. By pooling the frame-level features, utterance-level…

Generalized end-to-end (GE2E) model is widely used in speaker verification (SV) fields due to its expandability and generality regardless of specific languages. However, the long-short term memory (LSTM) based on GE2E has two limitations:…

Pre-trained deep learning embeddings have consistently shown superior performance over handcrafted acoustic features in speech emotion recognition (SER). However, unlike acoustic features with clear physical meaning, these embeddings lack…

Personal Voice Activity Detection (PVAD) is crucial for identifying target speaker segments in the mixture, yet its performance heavily depends on the quality of speaker embeddings. A key practical limitation is the short enrollment…

In this paper we investigate the use of adversarial domain adaptation for addressing the problem of language mismatch between speaker recognition corpora. In the context of speaker verification, adversarial domain adaptation methods aim at…

We address the problem of acoustic source separation in a deep learning framework we call "deep clustering." Rather than directly estimating signals or masking functions, we train a deep network to produce spectrogram embeddings that are…

Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers. It is well-known that large-margin training can improve the generalisation…

This paper proposes a method for extracting speaker embedding for each speaker from a variable-length recording containing multiple speakers. Speaker embeddings are crucial not only for speaker recognition but also for various multi-speaker…