相关论文: wav2letter++: The Fastest Open-source Speech Recog…

We propose a direct-to-word sequence model which uses a word network to learn word embeddings from letters. The word network can be integrated seamlessly with arbitrary sequence models including Connectionist Temporal Classification and…

We present DS-Serve, a framework that transforms large-scale text datasets, comprising half a trillion tokens, into a high-performance neural retrieval system. DS-Serve offers both a web interface and API endpoints, achieving low latency…

Several deep neural networks have recently been shown to generate activations similar to those of the brain in response to the same input. These algorithms, however, remain largely implausible: they require (1) extraordinarily large amounts…

This paper presents an end-to-end trainable fast scene text detector, named TextBoxes, which detects scene text with both high accuracy and efficiency in a single network forward pass, involving no post-process except for a standard…

Generating 3D human gestures and speech from a text script is critical for creating realistic talking avatars. One solution is to leverage separate pipelines for text-to-speech (TTS) and speech-to-gesture (STG), but this approach suffers…

Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…

In real-time speech recognition applications, the latency is an important issue. We have developed a character-level incremental speech recognition (ISR) system that responds quickly even during the speech, where the hypotheses are…

Transformers have become keystone models in natural language processing over the past decade. They have achieved great popularity in deep learning applications, but the increasing sizes of the parameter spaces required by transformer models…

While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind. To get us closer to general self-supervised…

The detection of software vulnerabilities (or vulnerabilities for short) is an important problem that has yet to be tackled, as manifested by the many vulnerabilities reported on a daily basis. This calls for machine learning methods for…

Autoregressive convolutional neural networks (CNNs) have been widely exploited for sequence generation tasks such as audio synthesis, language modeling and neural machine translation. WaveNet is a deep autoregressive CNN composed of several…

This work considers training neural networks for speaker recognition with a much smaller dataset size compared to contemporary work. We artificially restrict the amount of data by proposing three subsets of the popular VoxCeleb2 dataset.…

Wav2Prompt is proposed which allows straightforward integration between spoken input and a text-based large language model (LLM). Wav2Prompt uses a simple training process with only the same data used to train an automatic speech…

With the recent advances in technology, automatic speech recognition (ASR) has been widely used in real-world applications. The efficiency of converting large amounts of speech into text accurately with limited resources has become more…

This paper presents a transfer learning method in speech emotion recognition based on a Time-Delay Neural Network (TDNN) architecture. A major challenge in the current speech-based emotion detection research is data scarcity. The proposed…

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…

As deep neural networks become more complex and input datasets grow larger, it can take days or even weeks to train a deep neural network to the desired accuracy. Therefore, distributed Deep Learning at a massive scale is a critical…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. To improve robustness of speaker recognition system performance in…

In the paper we present an architecture of a keyword spotting (KWS) system that is based on modern neural networks, yields good performance on various types of speech data and can run very fast. We focus mainly on the last aspect and…

Audio-Visual Speech Recognition (AVSR) achieves robust speech recognition in noisy environments by combining auditory and visual information. However, recent Large Language Model (LLM) based AVSR systems incur high computational costs due…