arXiv subjects

Xinlu He

Publications and source records attributed to Xinlu He.

6 recordsLinked to original sources

arXiv2025

Continuous-Token Diffusion for Speaker-Referenced TTS in Multimodal LLMs

Unified architectures in multimodal large language models (MLLM) have shown promise in handling diverse tasks within a single framework. In the text-to-speech (TTS) task, current MLLM-based approaches rely on discrete token representations, which disregard the inherently continuous nature of speech and can lead to loss of fine-grained acoustic information. In this work, we investigate the TTS within the MLLM paradigm using continuous speech representations. We design a dual-head architecture and implement two complementary training strategies for a robust model. (1) A diffusion head generating continuous speech representations is added on the MLLM, which is on frame-level and strictly autoregressive. (2) The original language model head is retained to preserve multitask capability and to control the start and end of speech synthesis. (3) Masked training is employed to address exposure bias in autoregressive decoding. (4) To stabilize optimization, we propose a two-stage scheme where the LM is frozen in the second stage, ensuring the diffusion head learns from a fixed input distribution. Evaluations on LibriSpeech(PC) test-clean show that our approach achieves state-of-the-art autoregressive performance, with a WER of 1.95%, speaker similarity of 0.54, and UTMOS of 4.00. The two-stage training yields a 46% relative WER reduction over the one-stage training baseline. These results highlight the effectiveness of combining autoregressive modeling with continuous-token diffusion, supported by a two-stage training procedure.

eess.AS↗

arXiv2025

Interactive In-Meeting Speaker Correction with Human Feedback

Most automatic speech processing systems operate in ``open loop'' mode without user feedback about who said what, yet human-in-the-loop workflows can potentially enable higher accuracy. We propose an LLM-assisted in-meeting speaker correction system that lets users fix speaker attribution errors through brief corrective feedback. After performing streaming ASR and diarization, the system presents concise LLM-generated summaries to help users identify important speaker errors, and it incorporates user feedback by updating the speaker-attributed transcript and adding online speaker enrollments. To make this workflow effective despite errors in speech processing, LLM analysis, and user feedback, we developed several mechanisms to identify the intended correction more precisely. Further, we built an LLM-driven user feedback simulation to evaluate the workflow reprodubilty and at scale. Applied to the AMI headset test set, our system substantially reduces the DER from a streaming baseline (Google ASR + ECAPA) by 31.99% and speaker substitution error by 52.68%.

cs.CL↗

arXiv2025

Improving Speech Recognition of Named Entities in Classroom Speech with LLM Revision and Phonetic-Semantic Context

Classroom speech and lectures often contain named entities (NEs) such as names of people and special terminology. While automatic speech recognition (ASR) systems have achieved remarkable performance on general speech, the word error rate (WER) of state-of-the-art ASR remains high for named entities. Since NE are often the most critical keywords, misrecognizing them can affect all downstream applications, especially when the ASR functions as the front end of a complex system. In this paper, we introduce a large language model (LLM) revision pipeline to revise incorrect NEs in ASR predictions by leveraging not only the LLM's world knowledge and reasoning ability but also the available phonetic and semantic context. We also introduce the NER-MIT-OpenCourseWare dataset, containing 45 hours of data from MIT courses for development and testing. On this dataset, our proposed technique achieves up to 30\% relative WER reduction for NEs.

cs.CL↗

arXiv2025

Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio

Monaural multi-speaker automatic speech recognition (ASR) remains challenging due to data scarcity and the intrinsic difficulty of recognizing and attributing words to individual speakers, particularly in overlapping speech. Recent advances have driven the shift from cascade systems to end-to-end (E2E) architectures, which reduce error propagation and better exploit the synergy between speech content and speaker identity. Despite rapid progress in E2E multi-speaker ASR, the field lacks a comprehensive review of recent developments. This survey provides a systematic taxonomy of E2E neural approaches for multi-speaker ASR, highlighting recent advances and comparative analysis. Specifically, we analyze: (1) architectural paradigms (SIMO vs.~SISO) for pre-segmented audio, analyzing their distinct characteristics and trade-offs; (2) recent architectural and algorithmic improvements based on these two paradigms; (3) extensions to long-form speech, including segmentation strategy and speaker-consistent hypothesis stitching. Further, we (4) evaluate and compare methods across standard benchmarks. We conclude with a discussion of open challenges and future research directions towards building robust and scalable multi-speaker ASR.

cs.CL↗

arXiv2024

Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing

Recent work on discrete speech tokenization has paved the way for models that can seamlessly perform multiple tasks across modalities, e.g., speech recognition, text to speech, speech to speech translation. Moreover, large language models (LLMs) pretrained from vast text corpora contain rich linguistic information that can improve accuracy in a variety of tasks. In this paper, we present a decoder-only Discrete Multimodal Language Model (DMLM), which can be flexibly applied to multiple tasks (ASR, T2S, S2TT, etc.) and modalities (text, speech, vision). We explore several critical aspects of discrete multi-modal models, including the loss function, weight initialization, mixed training supervision, and codebook. Our results show that DMLM benefits significantly, across multiple tasks and datasets, from a combination of supervised and unsupervised training. Moreover, for ASR, it benefits from initializing DMLM from a pretrained LLM, and from a codebook derived from Whisper activations.

cs.CL↗

arXiv2021

Compositional Clustering: Applications to Multi-Label Object Recognition and Speaker Identification

We consider a novel clustering task in which clusters can have compositional relationships, e.g., one cluster contains images of rectangles, one contains images of circles, and a third (compositional) cluster contains images with both objects. In contrast to hierarchical clustering in which a parent cluster represents the intersection of properties of the child clusters, our problem is about finding compositional clusters that represent the union of the properties of the constituent clusters. This task is motivated by recently developed few-shot learning and embedding models can distinguish the label sets, not just the individual labels, assigned to the examples. We propose three new algorithms -- Compositional Affinity Propagation (CAP), Compositional k-means (CKM), and Greedy Compositional Reassignment (GCR) -- that can partition examples into coherent groups and infer the compositional structure among them. We show promising results, compared to popular algorithms such as Gaussian mixtures, Fuzzy c-means, and Agglomerative Clustering, on the OmniGlot and LibriSpeech datasets. Our work has applications to open-world multi-label object recognition and speaker identification & diarization with simultaneous speech from multiple speakers.

cs.LG↗