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 context, emotional cues, and semantic meaning that visual data alone often lacks. This paper proposes an audio-centric video understanding benchmark (ACVUBench) to evaluate the video comprehension capabilities of multimodal LLMs with a particular focus on auditory information. Specifically, ACVUBench incorporates 2,662 videos spanning 18 different domains with rich auditory information, together with over 13k high-quality human annotated or validated question-answer pairs. Moreover, ACVUBench introduces a suite of carefully designed audio-centric tasks, holistically testing the understanding of both audio content and audio-visual interactions in videos. A thorough evaluation across a diverse range of open-source and proprietary multimodal LLMs is performed, followed by the analyses of deficiencies in audio-visual LLMs. Demos are available at https://github.com/lark-png/ACVUBench.

These sources offer a wide range of video data from different websites, viewpoints, and domains. The relationship between these ten selected video datasets and others is shown in Figure 1. The videos from this ten datsets build the video pool for the further video selection. Notably, we use untrimmed videos from each source except for YouCook2 and Kinetics-700. We believe that cutting videos into clips can break the plot continuity, which is essential for understanding the videos. Based on the video pool, we aim to select dynamic videos. In Figure 1, we outline our criteria for selecting high-quality data. Our main method for identifying dynamic content involves using PySceneDetect, which calculates the number of scenes in a video We found that the number of scenes is a good indicator of video dynamism. Additionally, we have designed a specific approach to exclude videos that mainly contain "slides."

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 tackles different scenarios, leaving it impossible to generalize cross scenarios with new emerging capabilities. To this end, we introduce LLaVA-NeXT-Interleave, which simultaneously tackles Multi-image, Multi-frame (video), Multi-view (3D), and Multi-patch (single-image) scenarios in LMMs. To enable these capabilities, we regard the interleaved data format as a general template and compile the M4-Instruct dataset with 1,177.6k samples, spanning 4 primary domains with 14 tasks and 41 datasets. We also curate the LLaVA-Interleave Bench to comprehensively evaluate the multi-image performance of LMMs. Through extensive experiments, LLaVA-NeXT-Interleave achieves leading results in multi-image, video, and 3D benchmarks, while maintaining the performance of single-image tasks. Besides, our model also exhibits several emerging capabilities, e.g., transferring tasks across different settings and modalities. Code is available at https://github.com/LLaVA-VL/LLaVA-NeXT

Deep biasing for the Transducer can improve the recognition performance of rare words or contextual entities, which is essential in practical applications, especially for streaming Automatic Speech Recognition (ASR). However, deep biasing with large-scale rare words remains challenging, as the performance drops significantly when more distractors exist and there are words with similar grapheme sequences in the bias list. In this paper, we combine the phoneme and textual information of rare words in Transducers to distinguish words with similar pronunciation or spelling. Moreover, the introduction of training with text-only data containing more rare words benefits large-scale deep biasing. The experiments on the LibriSpeech corpus demonstrate that the proposed method achieves state-of-the-art performance on rare word error rate for different scales and levels of bias lists.

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 audio language music open neural network, built by integrating a pre-trained text-based large language model (LLM) with speech and audio encoders into a single multimodal model. SALMONN enables the LLM to directly process and understand general audio inputs and achieve competitive performances on a number of speech and audio tasks used in training, such as automatic speech recognition and translation, auditory-information-based question answering, emotion recognition, speaker verification, and music and audio captioning \textit{etc.} SALMONN also has a diverse set of emergent abilities unseen in the training, which includes but is not limited to speech translation to untrained languages, speech-based slot filling, spoken-query-based question answering, audio-based storytelling, and speech audio co-reasoning \textit{etc}. The presence of the cross-modal emergent abilities is studied, and a novel few-shot activation tuning approach is proposed to activate such abilities of SALMONN. To our knowledge, SALMONN is the first model of its type and can be regarded as a step towards AI with generic hearing abilities. An interactive demo of SALMONN is available at \texttt{\url{https://github.com/bytedance/SALMONN}}, and the training code and model checkpoints will be released upon acceptance.

Audio-visual large language models (LLM) have drawn significant attention, yet the fine-grained combination of both input streams is rather under-explored, which is challenging but necessary for LLMs to understand general video inputs. To this end, a fine-grained audio-visual joint representation (FAVOR) learning framework for multimodal LLMs is proposed in this paper, which extends a text-based LLM to simultaneously perceive speech and audio events in the audio input stream and images or videos in the visual input stream, at the frame level. To fuse the audio and visual feature streams into joint representations and to align the joint space with the LLM input embedding space, we propose a causal Q-Former structure with a causal attention module to enhance the capture of causal relations of the audio-visual frames across time. An audio-visual evaluation benchmark (AVEB) is also proposed which comprises six representative single-modal tasks with five cross-modal tasks reflecting audio-visual coreasoning abilities. While achieving competitive single-modal performance on audio, speech and image tasks in AVEB, FAVOR achieved over 20% accuracy improvements on the video question-answering task when fine-grained information or temporal causal reasoning is required. FAVOR, in addition, demonstrated remarkable video comprehension and reasoning abilities on tasks that are unprecedented by other multimodal LLMs. Text-based large language models (LLM) (Brown et al., 2020; Touvron et al., 2023; Chiang et al., 2023; Anil et al., 2023; Du et al., 2022) have demonstrated remarkable performance in various natural language processing tasks, especially achieving human-level capabilities in reasoning and comprehension (OpenAI, 2023). Meanwhile, instruction fine-tuning (Chung et al., 2022; Ouyang et al., 2022; Peng et al., 2023), where data is organised as pairs of user instruction (or prompt) and reference response, has emerged as a training paradigm that enables LLMs to perform various tasks by following open-ended natural language instructions from non-expert users. Recently, there has been a burgeoning research interest in equipping LLMs with visual and auditory perception abilities. These investigations often employ a trained modality alignment module that aligns the representation space of the input modality with the text one. Subsequently, work has started looking at incorporating multiple simultaneous input modalities (Su et al., 2023; Zhang et al., 2023b; Lyu et al., 2023; Zhao et al., 2023; Chen et al., 2023a). Despite the sequential nature of video and audio inputs, most aforementioned work treated video as a sampled subset of individual images and audio as a fixed-length spectrogram.

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 study of three commonly used structures as connectors, including fully connected layers, multi-head cross-attention, and Q-Former. Speech encoders from the Whisper model series as well as LLMs from the Vicuna model series with different model sizes were studied. Experiments were performed on the commonly used LibriSpeech, Common Voice, and GigaSpeech datasets, where the LLMs with Q-Formers demonstrated consistent and considerable word error rate (WER) reductions over LLMs with other connector structures. Q-Former-based LLMs can generalise well to out-of-domain datasets, where 12% relative WER reductions over the Whisper baseline ASR model were achieved on the Eval2000 test set without using any in-domain training data from Switchboard. Moreover, a novel segment-level Q-Former is proposed to enable LLMs to recognise speech segments with a duration exceeding the limitation of the encoders, which results in 17% relative WER reductions over other connector structures on 90-second-long speech data.

We propose PolyVoice, a language model-based framework for speech-to-speech translation (S2ST) system. Our framework consists of two language models: a translation language model and a speech synthesis language model. We use discretized speech units, which are generated in a fully unsupervised way, and thus our framework can be used for unwritten languages. For the speech synthesis part, we adopt the existing VALL-E X approach and build a unit-based audio language model. This grants our framework the ability to preserve the voice characteristics and the speaking style of the original speech. We examine our system on Chinese $\rightarrow$ English and English $\rightarrow$ Spanish pairs. Experimental results show that our system can generate speech with high translation quality and audio quality. Speech samples are available at https://speechtranslation.github.io/polyvoice.

In E2E systems, word timings can be estimated by the forced alignment results of character-level CTC models, where End-to-end (E2E) systems have shown comparable performance the CTC peak of the first character indicate the word start time to hybrid systems for automatic speech recognition and the CTC peak of the last character indicate the word end (ASR). Word timings, as a by-product of ASR, are essential time [9]. The CTC model cannot estimate word timings well in many applications, especially for subtitling and computeraided when the duration of the modeling unit is relatively long, e.g., pronunciation training. In this paper, we improve the Chinese characters. Because the blank probability of CTC frame-level classifier for word timings in E2E system by introducing model is dominant in almost all frames, and the non-blank probability label priors in connectionist temporal classification is only relatively high in few frames. This is called the (CTC) loss, which is adopted from prior works, and combining peaky behavior [10]. CTC-based alignments for word timings low-level Mel-scale filter banks with high-level ASR encoder can be improved by alleviating the peaky behavior [11, 12], output as input feature. On the internal Chinese corpus, but these methods have complicated regularization terms which the proposed method achieves 95.68%/94.18%

Domain adaptation using text-only corpus is challenging in end-to-end(E2E) speech recognition. Adaptation by synthesizing audio from text through TTS is resource-consuming. We present a method to learn Unified Speech-Text Representation in Conformer Transducer(USTR-CT) to enable fast domain adaptation using the text-only corpus. Different from the previous textogram method, an extra text encoder is introduced in our work to learn text representation and is removed during inference, so there is no modification for online deployment. To improve the efficiency of adaptation, single-step and multi-step adaptations are also explored. The experiments on adapting LibriSpeech to SPGISpeech show the proposed method reduces the word error rate(WER) by relatively 44% on the target domain, which is better than those of TTS method and textogram method. Also, it is shown the proposed method can be combined with internal language model estimation(ILME) to further improve the performance.