50 accepted papers
Code performance optimization is paramount in real-world software engineering and critical for production-level systems. While Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and bug fixing, their proficiency in enhancing code performance at the repository l…
Large Language Models (LLMs) can enhance their reasoning by interacting with external tools, a paradigm known as Tool-Integrated Reasoning (TIR). However, extending TIR to multi-turn settings using Reinforcement Learning (RL) often exhibits training instability and degraded performance. We attribute…
Long-duration streaming video understanding is fundamental for future AI agents, yet remains limited by ineffective long-term memory. We introduce video-SALMONN S, a memory-enhanced streaming audio-visual large language model that processes over 3-hour videos at $1$ FPS and $360$p resolution, outper…
Large Language Models (LLMs) generate functionally correct solutions but often fall short in code efficiency, a critical bottleneck for real-world deployment. In this paper, we introduce a novel test-time iterative optimization framework to address this, employing a closed-loop system where LLMs ite…
Audio often serves as an auxiliary modality in video understanding tasks of audio-visual large language models (LLMs), merely assisting in the comprehension of visual information. However, a thorough understanding of videos significantly depends on auditory information, as audio offers critical cont
Reinforcement learning (RL) has recently demonstrated strong potential in enhancing the reasoning capabilities of large language models (LLMs). Particularly, the "Zero" reinforcement learning introduced by Deepseek-R1-Zero, enables direct RL training of base LLMs without relying on an intermediate s…
Human vision is dynamic and continuous. However, in video understanding with multimodal large language models (LLMs), existing methods primarily rely on static features extracted from images sampled at a fixed low frame rate of frame-per-second (FPS) $\leqslant$2, leading to critical visual informat…
Visual instruction tuning has made considerable strides in enhancing the capabilities of Large Multimodal Models (LMMs). However, existing open LMMs largely focus on single-image tasks, their applications to multi-image scenarios remains less explored. Additionally, prior LMM research separately tac…
Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training for Video LLM with cheap automatic speech recognition (ASR) trans…
Numerous well-established studies have demonstrated the superhuman capabilities of modern Vision-Language Models (VLMs) across a wide range of tasks. However, growing is the doubt about the continuing availability of reliable high-quality labeling (supervision) from human annotators, leading to stag…
Recent advancements in vision-language models (VLMs) have improved performance by increasing the number of visual tokens, which are often significantly longer than text tokens. However, we observe that most real-world scenarios do not require such an extensive number of visual tokens. While the perf…
Linear attention mechanisms deliver significant advantages for Large Language Models (LLMs) by providing linear computational complexity, enabling efficient processing of ultra-long sequences (e.g., 1M context). However, existing Sequence Parallelism (SP) methods, essential for distributing these wo…
While recent advancements in reasoning optimization have significantly enhanced the capabilities of large language models (LLMs), existing efforts to improve reasoning have been limited to solving mathematical problems and focusing on visual graphical inputs, neglecting broader applications in gener…
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…
Extending multilingual automatic speech recognition (mASR) systems to new languages poses challenges, particularly when training data for existing languages is limited or unavailable. To tackle this issue, we suggest utilizing supplementary encoder and decoder components. Specifically, we propose ap…
Zero-shot text-to-speech (TTS) aims to synthesize voices with unseen speech prompts, which significantly reduces the data and computation requirements for voice cloning by skipping the fine-tuning process. However, the prompting mechanisms of zero-shot TTS still face challenges in the following aspe…
With the huge success of GPT models in natural language processing, there is a growing interest in applying language modeling approaches to speech tasks. Currently, the dominant architecture in speech-to-speech translation (S2ST) remains the encoder-decoder paradigm, creating a need to investigate t…
"We introduce RePOSE, a simple yet effective approach for addressing occlusion challenges in the learning of 3D human pose estimation (HPE) from videos. Conventional approaches typically employ absolute depth signals as supervision, which are adept at discernible keypoints but become less reliable w…
One-shot 3D talking portrait generation aims to reconstruct a 3D avatar from an unseen image, and then animate it with a reference video or audio to generate a talking portrait video. The existing methods fail to simultaneously achieve the goals of accurate 3D avatar reconstruction and stable talkin…
Multi-talker automatic speech recognition plays a crucial role in scenarios involving multi-party interactions, such as meetings and conversations. Due to its inherent complexity, this task has been receiving increasing attention. Notably, the serialized output training (SOT) stands out among variou…
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…
A typical fluency scoring system generally relies on an automatic speech recognition (ASR) system to obtain time stamps in input speech for the subsequent calculation of fluency-related features or directly modeling speech fluency with an end-to-end approach. This paper describes a novel ASR-free ap…
Image-based quick response (QR) code is frequently used, but creates barriers for the visual impaired people. With the goal of ``AI for good", this paper proposes the AudioQR, a barrier-free QR coding mechanism for the visually impaired population via deep neural audio watermarks. Previous audio wat…
Deep learning based methods have become a paradigm for cover song identification (CSI) in recent years, where the ByteCover systems have achieved state-of-the-art results on all the mainstream datasets of CSI. However, with the burgeon of short videos, many real-world applications require matching s…
ASR model deployment environment is ever-changing, and the incoming speech can be switched across different domains during a session. This brings a challenge for effective domain adaptation when only target domain text data is available, and our objective is to obtain obviously improved performance…
Recent studies on pronunciation scoring have explored the effect of introducing phone embeddings as reference pronunciation, but mostly in an implicit manner, i.e., addition or concatenation of reference phone embedding and actual pronunciation of the target phone as the phone-level pronunciation qu…
As a key component of automated speech recognition (ASR) and the front-end in text-to-speech (TTS), grapheme-to-phoneme (G2P) plays the role of converting letters to their corresponding pronunciations. Existing methods are either slow or poor in performance, and are limited in application scenarios,…
Virtual try-on is an important technology supporting online apparel shopping, which provides consumers with a virtual experience to fit garments without physically wearing them. Recently, the image-based virtual try-on has received growing research attention. However, the synthetic results of existi…
The deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications. However, computational resources for these networks are significantly constrained since they usually run on-call on edge devices. In this paper, we present BiFSMN, an accurate and extre…
Convolutional neural network (CNN)-based methods have dominated the recent research of cover song identification (CSI). A typical example is the ByteCover system we proposed, which has achieved state-of-the-art results on all the mainstream datasets of CSI. In this paper, we propose an up-graded ver…
Audio classification is an important task of mapping audio samples into their corresponding labels. Recently, the transformer model with self-attention mechanisms has been adopted in this field. However, existing audio transformers require large GPU memories and long training time, meanwhile relying…
Though achieving impressive results on many NLP tasks, the BERT-like masked language models (MLM) encounter the discrepancy between pre-training and inference. In light of this gap, we investigate the contextual representation of pre-training and inference from the perspective of word probability di…
Nowadays, most methods for end-to-end contextual speech recognition bias the recognition process towards contextual knowledge. Since all-neural contextual biasing methods rely on phrase-level contextual modeling and attention-based relevance modeling, they may suffer from the confusion between simil…
In the recent trend of semi-supervised speech recognition, both self-supervised representation learning and pseudo-labeling have shown promising results. In this paper, we propose a novel approach to combine their ideas for end-to-end speech recognition model. Without any extra loss function, we uti…
Unsupervised cross-lingual speech representation learning (XLSR) has recently shown promising results in speech recognition by leveraging vast amounts of unlabeled data across multiple languages. However, standard XLSR model suffers from language interference problem due to the lack of language spec…
In this paper, we propose S3T, a self-supervised pre-training method with Swin Transformer for music classification, aiming to learn meaningful music representations from massive easily accessible unlabeled music data. S3T introduces a momentum-based paradigm, MoCo, with Swin Transformer as its feat…
This paper describes our submission to ICASSP 2022 Multi-channel Multi-party Meeting Transcription (M2MeT) Challenge. For Track 1, we propose several approaches to make the clustering-based speaker diarization system enable to handle overlapped speech. Front-end dereverberation and the direction-of-…
Clothes style transfer for person video generation is a challenging task, due to drastic variations of intra-person appearance and video scenarios. To tackle this problem, most recent AdaIN-based architectures are proposed to extract clothes and scenario features for generation. However, these appro…
Deep learning techniques for separating audio into different sound sources face several challenges. Standard architectures require training separate models for different types of audio sources. Although some universal separators employ a single model to target multiple sources, they have difficulty…
In TTS-based audiobook production, multi-role dubbing and emotional expressions can significantly improve the naturalness of audiobooks. However, it requires manual annotation of original novels with explicit speaker and emotion tags in sentence level, which is extremely time-consuming and costly. I…
Well-labeled datasets available for melody extraction are scarce, which limits the further advancement of deep learning based methods. To overcome this problem, we propose to use a pitch refinement method to refine the semitone-level pitch sequences decoded from massive melody MIDI files to generate…
We present in this paper ByteCover, which is a new feature learning method for cover song identification (CSI). Byte-Cover is built based on the classical ResNet model, and two major improvements are designed to further enhance the capability of the model for CSI. In the first improvement, we introd…
The recurrent neural network transducer (RNN-T) model has been proved effective for keyword spotting (KWS) recently. However, compared with cross-entropy (CE) or connectionist temporal classification (CTC) based models, the additional prediction network in the RNN-T model increases the model size an…
Singing voice conversion (SVC) aims to convert the voice of one singer to that of other singers while keeping the singing content and melody. On top of recent voice conversion works, we propose a novel model to steadily convert songs while keeping their naturalness and intonation. We build an end-to…
Detecting anchor’s voice in live musical streams is an important preprocessing step for music and speech signal processing. Existing approaches to voice activity detection (VAD) primarily rely on audio, however, audio-based VAD is difficult to effectively focus on the target voice in noisy environme…
Convolutional neural network (CNN) based methods have achieved state-of-the-art performance for singing melody extraction from polyphonic music. However, most of these methods focus on the learning of local features, while relationships among spectral components locating far apart are often neglecte…
In this paper, we propose a hybrid text normalization system using multi-head self-attention. The system combines the advantages of a rule-based model and a neural model for text preprocessing tasks. Previous studies in Mandarin text normalization usually use a set of hand-written rules, which are h…
In Mandarin text-to-speech (TTS) system, the front-end text processing module significantly influences the intelligibility and naturalness of synthesized speech. Building a typical pipeline-based front-end which consists of multiple individual components requires extensive efforts. In this paper, we…