Symphony for Speech-to-Text: Supporting Real-Time Medical Voice Interfaces

• URL: http://arxiv.org/abs/2605.16545v2
• Date: Thu, 21 May 2026 17:52:56 GMT
• Title: Symphony for Speech-to-Text: Supporting Real-Time Medical Voice Interfaces
• Abstract summary: Symphony is a medical-grade speech recognition system for real-time streaming and batch file-based clinical use.<n>We show that Symphony substantially outperforms state-of-theart systems in clinical settings.<n>We release a clinical benchmark dataset to support reliable validation and further progress in medical speech recognition.
• Score: 2.2946642152815855
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: After decades of use in dictation and, more recently, ambient documentation, speech is emerging as a primary modality for interacting with technology and AI in healthcare. Yet medical speech recognition remains difficult: systems must capture specialized terminology, resolve contextual ambiguity, and render measurements, abbreviations, and clinical shorthand precisely. Existing solutions are typically optimized either for general-purpose transcription or narrow dictation workflows, limiting their reliability in safety-critical settings and their usefulness for broader clinical workflows. We introduce Symphony for Speech-to-Text, a medical-grade speech recognition system for real-time streaming and batch file-based clinical use. Symphony decomposes the transcription process into specialized components for recognition, formatting, and contextual correction to optimize medical term recall while producing clinically structured text in real time and adapting across use cases. Evaluations on public benchmark and medical speech datasets show that Symphony substantially outperforms state-of-the-art systems in clinical settings while matching or exceeding them in general-domain settings, suggesting robust generalization rather than overfitting. We release a clinical benchmark dataset to support reliable validation and further progress in medical speech recognition. Symphony is available through a production-grade API for live dictation, conversational transcription, and batch audio file processing.

Related papers

• Multi-Task Learning for Non-Canonical Phoneme Recognition via Articulatory Feature Decomposition [1.0737260344472548]
  Pathological and more broadly non-canonical speech present significant challenges for automatic phoneme recognition.<n>Existing phoneme recognition systems are typically trained on canonical speech and treat phonemes as atomic categorical labels.<n>We introduce a linguistically structured approach to non-canonical phoneme recognition that decomposes phoneme prediction into articulatory feature dimensions.
  arXiv  Detail & Related papers  (2026-08-23T08:03:18Z)
• SpeechDx: A Multi-Task Benchmark for Clinical Speech AI [7.379112766484577]
  Speech offers a uniquely informative window into health by simultaneously engaging neurological, motor, respiratory, and vocal systems.<n>Current clinical speech AI methods have largely progressed through isolated condition-specific studies.<n>We introduce SpeechDx, a large-scale benchmark for clinical speech AI spanning 12 datasets and 27 tasks across diverse health conditions.
  arXiv  Detail & Related papers  (2026-06-15T22:38:36Z)
• VIBEVOICE-ASR Technical Report [95.57263110940973]
  VibeVoice-ASR addresses challenges of context fragmentation and multi-speaker complexity in long-form audio.<n>It supports over 50 languages, requires no explicit language setting, and handles code-switching within and across utterances.
  arXiv  Detail & Related papers  (2026-01-26T06:11:51Z)
• MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance [66.74042564585942]
  MOSS-Speech is a true speech-to-speech large language model that directly understands and generates speech without relying on text guidance.<n>Our work establishes a new paradigm for expressive and efficient end-to-end speech interaction.
  arXiv  Detail & Related papers  (2025-10-01T04:32:37Z)
• Automatic Speech Recognition for Greek Medical Dictation [5.543902482518564]
  The main objective of this paper is to create a domain-specific system for Greek medical speech transcriptions.<n>We develop a system that combines automatic speech recognition techniques with text correction model.
  arXiv  Detail & Related papers  (2025-09-28T01:15:47Z)
• Benchmarking Automatic Speech Recognition coupled LLM Modules for Medical Diagnostics [0.0]
  This report serves as my self project wherein models finetuned on medical call recordings are analysed.<n> Automatic Speech Recognition (ASR) for speech transcription and a Large Language Model (LLM) for context-aware, professional responses are analysed.
  arXiv  Detail & Related papers  (2025-02-18T14:05:13Z)
• Application of Audio Fingerprinting Techniques for Real-Time Scalable Speech Retrieval and Speech Clusterization [0.0]
  This paper offers fresh insights into adapting existing techniques to address the specialized challenge of speech retrieval.<n>The focus is on achieving rapid and accurate audio retrieval in batch processing instead of facilitating single requests.<n>The paper demonstrates how this approach can be utilized to support audio clustering based on speech transcripts without undergoing actual speech-to-text conversion.
  arXiv  Detail & Related papers  (2024-10-29T09:11:28Z)
• Searching for Best Practices in Medical Transcription with Large Language Model [1.0855602842179624]
  This paper introduces a novel approach leveraging a Large Language Model (LLM) to generate highly accurate medical transcripts. Our methodology integrates advanced language modeling techniques to lower the Word Error Rate (WER) and ensure the precise recognition of critical medical terms.
  arXiv  Detail & Related papers  (2024-10-04T03:41:16Z)
• Show from Tell: Audio-Visual Modelling in Clinical Settings [58.88175583465277]
  We consider audio-visual modelling in a clinical setting, providing a solution to learn medical representations without human expert annotation. A simple yet effective multi-modal self-supervised learning framework is proposed for this purpose. The proposed approach is able to localise anatomical regions of interest during ultrasound imaging, with only speech audio as a reference.
  arXiv  Detail & Related papers  (2023-10-25T08:55:48Z)
• Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis [67.73554826428762]
  We propose a novel audio-visual speech enhancement framework for high-fidelity telecommunications in AR/VR. Our approach leverages audio-visual speech cues to generate the codes of a neural speech, enabling efficient synthesis of clean, realistic speech from noisy signals.
  arXiv  Detail & Related papers  (2022-03-31T17:57:10Z)
• Towards more patient friendly clinical notes through language models and ontologies [57.51898902864543]
  We present a novel approach to automated medical text based on word simplification and language modelling. We use a new dataset pairs of publicly available medical sentences and a version of them simplified by clinicians. Our method based on a language model trained on medical forum data generates simpler sentences while preserving both grammar and the original meaning.
  arXiv  Detail & Related papers  (2021-12-23T16:11:19Z)
• Clinical Named Entity Recognition using Contextualized Token Representations [49.036805795072645]
  This paper introduces the technique of contextualized word embedding to better capture the semantic meaning of each word based on its context. We pre-train two deep contextualized language models, Clinical Embeddings from Language Model (C-ELMo) and Clinical Contextual String Embeddings (C-Flair) Explicit experiments show that our models gain dramatic improvements compared to both static word embeddings and domain-generic language models.
  arXiv  Detail & Related papers  (2021-06-23T18:12:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.