Related papers: Length- and Noise-aware Training Techniques for Sh…
This paper explores applying the wav2vec2 framework to speaker recognition instead of speech recognition. We study the effectiveness of the pre-trained weights on the speaker recognition task, and how to pool the wav2vec2 output sequence…
Contemporary speech enhancement predominantly relies on audio transforms that are trained to reconstruct a clean speech waveform. The development of high-performing neural network sound recognition systems has raised the possibility of…
Speaker verification (SV) has recently attracted considerable research interest due to the growing popularity of virtual assistants. At the same time, there is an increasing requirement for an SV system: it should be robust to short speech…
In speaker verification systems, the utilization of short utterances presents a persistent challenge, leading to performance degradation primarily due to insufficient phonetic information to characterize the speakers. To overcome this…
In this paper, we propose an iterative framework for self-supervised speaker representation learning based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing…
Far-field speech recognition is a challenging task that conventionally uses signal processing beamforming to attack noise and interference problem. But the performance has been found usually limited due to heavy reliance on environmental…
In this paper, we apply a latent class model (LCM) to the task of speaker diarization. LCM is similar to Patrick Kenny's variational Bayes (VB) method in that it uses soft information and avoids premature hard decisions in its iterations.…
Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise or reverberation. However, such speech enhancement techniques…
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…
Teleconferencing is becoming essential during the COVID-19 pandemic. However, in real-world applications, speech quality can deteriorate due to, for example, background interference, noise, or reverberation. To solve this problem, target…
The conventional speaker recognition frameworks (e.g., the i-vector and CNN-based approach) have been successfully applied to various tasks when the channel of the enrolment dataset is similar to that of the test dataset. However, in…
Trans-dimensional random field language models (TRF LMs) where sentences are modeled as a collection of random fields, have shown close performance with LSTM LMs in speech recognition and are computationally more efficient in inference.…
Speech recognition and translation systems perform poorly on noisy inputs, which are frequent in realistic environments. Augmenting these systems with visual signals has the potential to improve robustness to noise. However, audio-visual…
Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In practical scenarios,…
For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…
Under noisy environments, to achieve the robust performance of speaker recognition is still a challenging task. Motivated by the promising performance of multi-task training in a variety of image processing tasks, we explore the potential…
Most speech enhancement algorithms make use of the short-time Fourier transform (STFT), which is a simple and flexible time-frequency decomposition that estimates the short-time spectrum of a signal. However, the duration of short STFT…
Attention-based sequence-to-sequence automatic speech recognition (ASR) requires a significant delay to recognize long utterances because the output is generated after receiving entire input sequences. Although several studies recently…
We propose an algorithm to denoise speakers from a single microphone in the presence of non-stationary and dynamic noise. Our approach is inspired by the recent success of neural network models separating speakers from other speakers and…
We present an approach to tackle the speaker recognition problem using Triplet Neural Networks. Currently, the $i$-vector representation with probabilistic linear discriminant analysis (PLDA) is the most commonly used technique to solve…