mlsanityData to 19 Oct 2026

Speech and audio language models

11 directions · 8,980 papers · 15 this week

Busiest this week

Most new since Mon 19 Oct

Speech recognition models and training

1,811 papers3 this weekMedium confidence in this grouping: mostly one topic, with blurry edgesMedium confidence in this grouping: mostly one topic, with blurry edges · About

  1. Preference-Aware Pareto Steering for Multi-Task Speech LLMs
  2. Think Before You Transcribe: Context-Steered Reasoning for Hotword-Aware Speech Recognition
  3. PronCFT: Pronunciation Contextual Fine-Tuning for Contextual Biasing of Out-of-Vocabulary Words in LLM-Based ASR
Open →

All directions

Largest first · week from Mon 19 Oct

  1. Speech recognition models and trainingasr, speech, recognition, speech recognitionMedium confidence in this grouping: mostly one topic, with blurry edges · About1,8113Medium confidence in this grouping: mostly one topic, with blurry edges
  2. Vocoders and speech synthesisspeech, tts, synthesis, text-to-speechMedium confidence in this grouping: mostly one topic, with blurry edges · About1,6312Medium confidence in this grouping: mostly one topic, with blurry edges
  3. Multilingual and low-resource ASRspeech, asr, languages, recognitionMedium confidence in this grouping: mostly one topic, with blurry edges · About1,0753Medium confidence in this grouping: mostly one topic, with blurry edges
  4. Speech enhancement and noise suppressionenhancement, speech enhancement, speech, noiseHigh confidence in this grouping: the papers form one clear topic · About8920High confidence in this grouping: the papers form one clear topic
  5. Speaker recognition and diarizationspeaker, diarization, verification, speaker verificationHigh confidence in this grouping: the papers form one clear topic · About8322High confidence in this grouping: the papers form one clear topic
  6. Audio language models and spoken dialogueaudio, reasoning, dialogue, spokenMedium confidence in this grouping: mostly one topic, with blurry edges · About7391Medium confidence in this grouping: mostly one topic, with blurry edges
  7. ASR evaluation, bias and atypical speechspeech, asr, recognition, speech recognitionLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About6443Low confidence in this grouping: the papers may belong to more than one topic, or the group may change
  8. Anti-spoofing and adversarial audio attacksattacks, audio, adversarial, detectionHigh confidence in this grouping: the papers form one clear topic · About4490High confidence in this grouping: the papers form one clear topic
  9. Speech translationtranslation, speech translation, speech, simultaneousHigh confidence in this grouping: the papers form one clear topic · About3650High confidence in this grouping: the papers form one clear topic
  10. Audio-visual speech recognitionvisual, audio-visual, recognition, signHigh confidence in this grouping: the papers form one clear topic · About2830High confidence in this grouping: the papers form one clear topic
  11. Emotional speech synthesis and recognitionemotion, emotional, speech, emotion recognitionMedium confidence in this grouping: mostly one topic, with blurry edges · About2591Medium confidence in this grouping: mostly one topic, with blurry edges

Weekly activity

Papers per week, 6 Jul – 19 Oct (last week partial)

  1. DirectionConfidencepapers16 wks
  2. Audio language models and spoken dialogueMedium confidence in this grouping: mostly one topic, with blurry edges · AboutMedium confidence in this grouping: mostly one topic, with blurry edgesPer week: 6 Jul: 8; 13 Jul: 3; 20 Jul: 8; 27 Jul: 7; 3 Aug: 7; 10 Aug: 6; 17 Aug: 5; 24 Aug: 19; 31 Aug: 13; 7 Sep: 15; 14 Sep: 18; 21 Sep: 25; 28 Sep: 17; 5 Oct: 11; 12 Oct: 14; 19 Oct: 1739177
  3. Vocoders and speech synthesisMedium confidence in this grouping: mostly one topic, with blurry edges · AboutMedium confidence in this grouping: mostly one topic, with blurry edgesPer week: 6 Jul: 7; 13 Jul: 9; 20 Jul: 7; 27 Jul: 5; 3 Aug: 12; 10 Aug: 10; 17 Aug: 3; 24 Aug: 3; 31 Aug: 10; 7 Sep: 17; 14 Sep: 11; 21 Sep: 16; 28 Sep: 16; 5 Oct: 16; 12 Oct: 7; 19 Oct: 21,631151
  4. Multilingual and low-resource ASRMedium confidence in this grouping: mostly one topic, with blurry edges · AboutMedium confidence in this grouping: mostly one topic, with blurry edgesPer week: 6 Jul: 9; 13 Jul: 2; 20 Jul: 5; 27 Jul: 2; 3 Aug: 1; 10 Aug: 8; 17 Aug: 3; 24 Aug: 4; 31 Aug: 3; 7 Sep: 6; 14 Sep: 5; 21 Sep: 16; 28 Sep: 10; 5 Oct: 5; 12 Oct: 8; 19 Oct: 31,07590
  5. Speech recognition models and trainingMedium confidence in this grouping: mostly one topic, with blurry edges · AboutMedium confidence in this grouping: mostly one topic, with blurry edgesPer week: 6 Jul: 8; 13 Jul: 2; 20 Jul: 2; 27 Jul: 2; 3 Aug: 3; 10 Aug: 2; 17 Aug: 3; 24 Aug: 4; 31 Aug: 3; 7 Sep: 7; 14 Sep: 12; 21 Sep: 17; 28 Sep: 5; 5 Oct: 10; 12 Oct: 6; 19 Oct: 31,81189
  6. ASR evaluation, bias and atypical speechLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · AboutLow confidence in this grouping: the papers may belong to more than one topic, or the group may changePer week: 6 Jul: 3; 13 Jul: 3; 20 Jul: 7; 27 Jul: 2; 3 Aug: 2; 10 Aug: 2; 17 Aug: 1; 24 Aug: 3; 31 Aug: 6; 7 Sep: 4; 14 Sep: 4; 21 Sep: 6; 28 Sep: 5; 5 Oct: 6; 12 Oct: 9; 19 Oct: 364466
  7. Speaker recognition and diarizationHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 6 Jul: 5; 13 Jul: 4; 20 Jul: 4; 27 Jul: 1; 3 Aug: 2; 10 Aug: 2; 17 Aug: 3; 24 Aug: 1; 31 Aug: 3; 7 Sep: 6; 14 Sep: 3; 21 Sep: 9; 28 Sep: 5; 5 Oct: 5; 12 Oct: 2; 19 Oct: 283257
  8. Anti-spoofing and adversarial audio attacksHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 6 Jul: 0; 13 Jul: 4; 20 Jul: 2; 27 Jul: 4; 3 Aug: 2; 10 Aug: 4; 17 Aug: 0; 24 Aug: 1; 31 Aug: 5; 7 Sep: 4; 14 Sep: 8; 21 Sep: 10; 28 Sep: 8; 5 Oct: 4; 12 Oct: 1; 19 Oct: 044957
  9. Speech enhancement and noise suppressionHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 6 Jul: 3; 13 Jul: 1; 20 Jul: 1; 27 Jul: 1; 3 Aug: 2; 10 Aug: 8; 17 Aug: 6; 24 Aug: 1; 31 Aug: 7; 7 Sep: 5; 14 Sep: 7; 21 Sep: 10; 28 Sep: 6; 5 Oct: 2; 12 Oct: 3; 19 Oct: 089263
  10. Emotional speech synthesis and recognitionMedium confidence in this grouping: mostly one topic, with blurry edges · AboutMedium confidence in this grouping: mostly one topic, with blurry edgesPer week: 6 Jul: 1; 13 Jul: 1; 20 Jul: 0; 27 Jul: 2; 3 Aug: 2; 10 Aug: 1; 17 Aug: 1; 24 Aug: 3; 31 Aug: 1; 7 Sep: 2; 14 Sep: 1; 21 Sep: 2; 28 Sep: 5; 5 Oct: 3; 12 Oct: 1; 19 Oct: 125927
  11. Speech translationHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 6 Jul: 0; 13 Jul: 1; 20 Jul: 2; 27 Jul: 0; 3 Aug: 1; 10 Aug: 0; 17 Aug: 0; 24 Aug: 0; 31 Aug: 1; 7 Sep: 4; 14 Sep: 0; 21 Sep: 3; 28 Sep: 2; 5 Oct: 3; 12 Oct: 0; 19 Oct: 036517
  12. Audio-visual speech recognitionHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 6 Jul: 5; 13 Jul: 1; 20 Jul: 0; 27 Jul: 2; 3 Aug: 0; 10 Aug: 0; 17 Aug: 0; 24 Aug: 2; 31 Aug: 0; 7 Sep: 2; 14 Sep: 1; 21 Sep: 5; 28 Sep: 0; 5 Oct: 0; 12 Oct: 3; 19 Oct: 028321