24 accepted papers
Large language models (LLMs) have demonstrated impressive reasoning capabilities by scaling test-time compute via long Chain-of-Thought (CoT). However, recent findings suggest that raw token counts are unreliable proxies for reasoning quality: increased generation length does not consistently correl…
"While reconstructing human poses in 3D from inexpensive sensors has advanced significantly in recent years, quantifying the dynamics of human motion, including the muscle-generated joint torques and external forces, remains a challenge. Prior attempts to estimate physics from reconstructed human po…
Generating high-quality images that conform to the semantics of captions has numerous potential applications. However, text-to-image generation is a challenging task due to its cross-modality nature. Current generative models are typically unstable, meaning that complex sentences can result in poor…
The impressive capability and versatility of large language models (LLMs) have aroused increasing attention in automatic speech recognition (ASR), with several pioneering studies attempting to build integrated ASR models by connecting a speech encoder with an LLM. This paper presents a comparative s…
Multimodal large language models (LLMs) have shown promising visual perception abilities by connecting with image encoders, but their performance on auditory tasks has not yet been widely investigated. Meanwhile, automatic speech recognition (ASR) and automatic audio captioning (AAC) are often achie…
Hearing is arguably an essential ability of artificial intelligence (AI) agents in the physical world, which refers to the perception and understanding of general auditory information consisting of at least three types of sounds: speech, audio events, and music. In this paper, we propose SALMONN, a…
Speech understanding as an element of the more generic video understanding using audio-visual large language models (av-LLMs) is a crucial yet understudied aspect. This paper proposes video-SALMONN, a single end-to-end av-LLM for video processing, which can understand not only visual frame sequences…
Adapting End-to-End (E2E) models to unseen domains is still a big challenge since training E2E models requires lots of paired audio and text training data. We propose a novel domain adaptation framework for the E2E model, which only uses the text of the target domain. Moreover, the proposed methods…
Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years , but suffer from blur and severe semantics loss at extremely low bitrates. To address this issue, we propose a multimodal machine learning me…
Punctuation prediction is essential for automatic speech recognition (ASR). Although many works have been proposed for punctuation prediction, the on-device scenarios are rarely discussed with an end-to-end ASR. The punctuation prediction task is often treated as a post-processing of ASR outputs, bu…
Always-on keyword spotting (KWS), i.e., wake word detection, has been widely used in many voice assistant applications running on smart devices. Although fixed wakeup word detection trained on specifically collected data has reached high performance, it is still challenging to build an arbitrarily c…
This paper describes the AISpeech-SJTU ASR system for the Interspeech-2020 Accented English Speech Recognition Challenge (AESRC). This task is challenging due to the diversity of pronunciation accuracy, intonation speed and pronunciation of some syllables. All participants were restricted to develop…
This letter describes a novel grasp quality measure that we developed for evaluating antipodal grasp poses in real-time. To quantify the grasp quality, we compute a set of object movement features from analyzing the interaction between the gripper and the object's projections in the image space. The
In sim-to-real transfer of Reinforcement Learning (RL) policies for robot tasks, Domain Randomization (DR) is a widely used technique for improving adaptability. However, in DR there is a conflict between adaptability and training stability, and heavy DR tends to result in instability or even failur…
Goal-conditioned hierarchical reinforcement learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the goal space, is often large. Searching in a large goal space…
Deep neural network (DNN) has achieved the state-of-the-art performance in automatic speech recognition (ASR). However, the meaning of parameters and neurons are hard to be interpreted in DNNs, which makes the regularizations and adaptation of DNNs difficult. In this work, we aim to do effective and…
Data augmentation is an effective method to increase the size of training data and reduce the mismatch between training and testing for noise robust speech recognition. Different from the traditional approaches by directly adding noise to the original waveform, in this work we utilize generative adv…
This paper proposes a framework that combines teacher-student training and permutation invariant training (PIT) for single-channel multi-talker speech recognition. In contrast to most of conventional teacher-student training methods that aim at compressing the model, the proposed method distills kno…
Although great progress has been made in automatic speech recognition (ASR), significant performance degradation still exists in noisy environments. Based on our previous introduced very deep CNNs, this paper further integrates residual learning to evaluate very deep convolutional residual network (…
Far-field speech recognition is an important yet challenging task due to low signal to noise ratio. In this paper, three novel deep neural network architectures are explored to improve the far-field speech recognition accuracy by exploiting the parallel far-field and close-talk recordings. All three…
Although great progress has been made in automatic speech recognition (ASR), significant performance degradation still exists in distant talking scenarios due to significantly lower signal power. In this paper, a novel adaptation framework, named integrated adaptation with multi-factor joint-learnin…
Deep neural networks (DNNs) for acoustic modeling have been shown to provide impressive results on many state-of-the-art automatic speech recognition (ASR) applications. However, DNN performance degrades due to mismatches in training and testing conditions and thus adaptation is necessary. In this p…
Long Short-Term Memory (LSTM) is a particular type of recurrent neural network (RNN) that can model long term temporal dynamics. Recently it has been shown that LSTM-RNNs can achieve higher recognition accuracy than deep feed-forword neural networks (DNNs) in acoustic modelling. However, speaker ada…
Although context-dependent DNN-HMM systems have achieved significant improvements over GMM-HMM systems, there still exists big performance degradation if the acoustic condition of the test data mismatches that of the training data. Hence, adaptation and adaptive training of DNN are of great research…