INTERSPEECH 2022

home

Call for

Important Dates

Program at a Glance

home

Program at a Glance

Download Abstract Book Get a Whole Proceedings Last Updated : 2022.11.22

Last Updated : 2022.09.16

Last Updated : 2022.09.13

Technical Program

September 19th, Monday

Mon, 19 Sep, 11:00 - 13:00(KST)

Mon-O-OS-1-1: Speech Synthesis: Toward end-to-end synthesis

On-Site Oral R104-106
Mon-O-OS-1-2: Technology for disordered speech

On-Site Oral R107-109
Mon-O-OS-1-3: Neural network training methods for ASR I

On-Site Oral R110-111
Mon-O-OS-1-4: Acoustic phonetics and prosody

On-Site Oral R113-115
Mon-O-OS-1-5: Spoken Machine Translation

On-Site Oral R116-118
Mon-P-OS-1-1: (Multimodal) Speech Emotion Recognition I

On-Site Poster Premier Ballroom
Mon-P-OS-1-2: Dereverberation, noise reduction, and speaker extraction

On-Site Poster Premier Ballroom
Mon-P-OS-1-3: Source Separation II

On-Site Poster Premier Ballroom
Mon-P-VR-1-4: Embedding and Network Architecture for Speaker Recognition

Virtual Poster
Mon-P-VR-1-5: Speech representation II

Virtual Poster
Mon-P-VR-1-6: Speech Synthesis: Linguistic processing, paradigms and other topics II

Virtual Poster
Mon-P-VR-1-7: Other Topics in Speech Recognition

Virtual Poster
Mon-SS-VR-1-8: Audio Deep PLC (Packet Loss Concealment) Challenge

Virtual SS

Technical Program

September 19th, Monday

Mon, 19 Sep, 14:30 – 16:30(KST)

Mon-O-OS-2-1: Robust Speaker Recognition

On-Site Oral R104-106
Mon-O-OS-2-2: Speech Production

On-Site Oral R107-109
Mon-O-OS-2-3: Speech quality assessment

On-Site Oral R110-111
Mon-O-OS-2-4: Language Modeling and Lexical modeling for ASR

On-Site Oral R113-115
Mon-SS-OS-2-5: Challenges and opportunities for signal processing and machine learning for multiple smart devices

On-Site SS R116-118
Mon-P-OS-2-1: Speech processing & measurement

On-Site Poster Premier Ballroom
Mon-P-OS-2-2: Speech Synthesis: Acoustic Modeling and Neural Waveform Generation I

On-Site Poster Premier Ballroom
Mon-ST-OS-2-3: Show and Tell I

On-Site Show&Tell Premier Ballroom
Mon-P-VR-2-4: Spatial audio

Virtual Poster
Mon-P-VR-2-5: Single-channel speech enhancement II

Virtual Poster
Mon-P-VR-2-6: Novel models and training methods for ASR II

Virtual Poster
Mon-P-VR-2-7: Spoken dialogue systems and multimodality

Virtual Poster
Mon-ST-VR-2-8: Show and Tell I

Virtual Show&Tell

Technical Program

September 20th, Tuesday

Tue, 20 Sep, 10:00 – 12:00(KST)

Tue-O-OS-3-1: Speech Emotion Recognition

On-Site Oral R104-106
Tue-O-OS-3-2: Single-channel speech enhancement I

On-Site Oral R107-109
Tue-O-OS-3-3: Speech Synthesis: New applications

On-Site Oral R110-111
Tue-O-OS-3-4: Spoken language understanding I

On-Site Oral R113-115
Tue-SS-OS-3-5: Inclusive and Fair Speech Technologies I (oral) + II (poster)

On-Site SS R116-118
Tue-P-OS-3-1: Phonetics I

On-Site Poster Premier Ballroom
Tue-P-OS-3-2: Multi-, cross-lingual and other topics in ASR I

On-Site Poster Premier Ballroom
Tue-P-OS-3-3: Zero, low-resource and multi-modal speech recognition I

On-Site Poster Premier Ballroom
Tue-P-VR-3-4: Speaker Embedding and Diarization

Virtual Poster
Tue-P-VR-3-5:Acoustic event detection and classification

Virtual Poster
Tue-P-VR-3-6: Speech Synthesis: Acoustic Modeling and Neural Waveform Generation II

Virtual Poster
Tue-P-VR-3-7: ASR: Architecture and Search

Virtual Poster
Tue-P-VR-3-8: Spoken Language Processing II

Virtual Poster

Technical Program

September 20th, Tuesday

Tue, 20 Sep, 13:30 – 15:30(KST)

Tue-O-OS-4-1: Source Separation I

On-Site Oral R104-106
Tue-O-OS-4-2: ASR Technologies and systems

On-Site Oral R107-109
Tue-O-OS-4-3: Speech Perception

On-Site Oral R110-111
Tue-O-OS-4-4: Spoken Term Detection and Voice Search

On-Site Oral R113-115
Tue-SS-OS-4-5: Speech and language in health: from remote monitoring to medical conversations I

On-Site SS R116-118
Tue-P-OS-4-1: Speech Synthesis: Linguistic processing, paradigms and other topics I

On-Site Poster Premier Ballroom
Tue-ST-OS-4-2: Show and Tell II

On-Site Show&Tell Premier Ballroom
Tue-P-VR-4-3: Multimodal Speech Emotion Recognition and Paralinguistics

Virtual Poster
Tue-P-VR-4-4: Neural Transducers, Streaming ASR and novel ASR models

Virtual Poster
Tue-P-VR-4-5: Zero, low-resource and multi-modal speech recognition II

Virtual Poster
Tue-P-VR-4-6: Atypical speech analysis and detection

Virtual Poster

Technical Program

September 20th, Tuesday

Tue, 20 Sep, 16:00 – 18:00(KST)

Tue-O-OS-5-1: Adaptation, Transfer learning, and distillation for ASR

On-Site Oral R104-106
Tue-O-OS-5-2: Speaker and language Recogntion I

On-Site Oral R107-109
Tue-O-OS-5-3: Pathological Speech Analysis

On-Site Oral R110-111
Tue-O-OS-5-4: Cross/Multi-lingual ASR

On-Site Oral R113-115
Tue-SS-OS-5-5: Speaking Styles and Interaction Styles I (oral) + II (poster)

On-Site SS R116-118
Tue-P-OS-5-1: Speech Synthesis: Tools, Data, and Evaluation

On-Site Poster Premier Ballroom
Tue-P-OS-5-2: Acoustic signal representation and analysis II

On-Site Poster Premier Ballroom
Tue-SS-OS-5-3: Speech and language in health: from remote monitoring to medical conversations II

On-Site SS Premier Ballroom
Tue-P-VR-5-4: Dereverberation and echo cancellation

Virtual Poster
Tue-P-VR-5-5: Voice Conversion and Adaptation III

Virtual Poster
Tue-P-VR-5-6: Novel models and training methods for ASR III

Virtual Poster
Tue-P-VR-5-7: Spoken language modeling and understanding

Virtual Poster

Technical Program

September 21th, Wednesday

Wed, 21 Sep, 10:00 - 12:00(KST)

Wed-O-OS-6-1: Acoustic signal representation and analysis I

On-Site Oral R104-106
Wed-O-OS-6-2: Privacy and security in speech communication

On-Site Oral R107-109
Wed-O-OS-6-3: Multimodal systems

On-Site Oral R110-111
Wed-O-OS-6-4: Atypical Speech Detection

On-Site Oral R113-115
Wed-SS-OS-6-5: Spoofing-Aware Automatic Speaker Verification (SASV) I

On-Site SS R116-118
Wed-P-OS-6-1: Single-channel and multi-channel speech enhancement

On-Site Poster Premier Ballroom
Wed-P-OS-6-2: Voice Conversion and Adaptation II

On-Site Poster Premier Ballroom
Wed-P-OS-6-3: Resource-constrained ASR

On-Site Poster Premier Ballroom
Wed-P-VR-6-4: Speech production, perception and multimodality

Virtual Poster
Wed-P-VR-6-5: Multi-, cross-lingual and other topics in ASR II

Virtual Poster
Wed-P-VR-6-6: Spoken Language Processing III

Virtual Poster
Wed-SS-VR-6-7: Non-intrusive Objective Speech Quality Assessment (NISQA) Challenge for Online Conferencing Applications

Virtual SS
Wed-SS-VR-6-8: Speech and language in health: from remote monitoring to medical conversations III

Virtual SS

Technical Program

September 21th, Wednesday

Wed, 21 Sep, 13:30 - 15:30(KST)

Wed-O-OS-7-1: Speech synthesis: Prosody Modeling

On-Site Oral R104-106
Wed-O-OS-7-2: Self-supervised, semi-supervised, adaptation and data augmentation for ASR

On-Site Oral R107-109
Wed-O-OS-7-3: Phonetics and Phonology

On-Site Oral R110-111
Wed-O-OS-7-4: spoken language understanding II

On-Site Oral R113-115
Wed-SS-OS-7-5: Speech Intelligibility Prediction for Hearing-Impaired Listeners I

On-Site SS R116-118
Wed-SS-OS-7-1: Low-Resource ASR Development I

On-Site SS Premier Ballroom
Wed-P-OS-7-2: Speech representation I

On-Site Poster Premier Ballroom
Wed-P-OS-7-3: Pathological Speech Assessment

On-Site Poster Premier Ballroom
Wed-ST-OS-7-4: Show and Tell III

On-Site Show&Tell Premier Ballroom
Wed-P-VR-7-5: Speaker and Language Recognition II

Virtual Poster
Wed-P-VR-7-6: Speech segmentation II

Virtual Poster
Wed-P-VR-7-7: Robust ASR, and far-field/multi-talker ASR

Virtual Poster
Wed-P-VR-7-8: ASR: Linguistic Components

Virtual Poster
Wed-SS-VR-7-9: Speech Intelligibility Prediction for Hearing-Impaired Listeners II

Virtual SS
Wed-ST-VR-7-10: Show and Tell III

Virtual Show&Tell

Technical Program

September 21th, Wednesday

Wed, 21 Sep, 16:00 - 18:00(KST)

Wed-O-OS-8-1: Summarization, Entity Extraction, Evaluation and Others

On-Site Oral R104-106
Wed-O-OS-8-2: Automatic analysis of paralinguistics

On-Site Oral R107-109
Wed-O-OS-8-3: Self Supervision and Anti-Spoofing

On-Site Oral R110-111
Wed-O-OS-8-4: Speech articulation & neural processing

On-Site Oral R113-115
Wed-SS-OS-8-5: Low Resource Spoken Language Understanding + Non-intrusive Objective Speech Quality Assessment (NISQA) Challenge for Online Conferencing Applications

On-Site SS R116-118
Wed-P-OS-8-1: Novel models and training methods for ASR I

On-Site Poster Premier Ballroom
Wed-P-VR-8-2: Acoustic scene analysis

Virtual Poster
Wed-P-VR-8-3: Speech coding and privacy

Virtual Poster
Wed-P-VR-8-4: Speech Synthesis: Singing, Multimodal, Crosslingual Synthesis

Virtual Poster
Wed-P-VR-8-5: Applications in transcription, education and learning II

Virtual Poster
Wed-SS-VR-8-6: Spoofing-Aware Automatic Speaker Verification (SASV) II

Virtual SS

Technical Program

September 22th, Thursday

Thu, 22 Sep, 10:00 - 12:00(KST)

Thu-O-OS-9-1: Speech Coding and Restoration

On-Site Oral R104-106
Thu-O-OS-9-2: Streaming ASR

On-Site Oral R107-109
Thu-O-OS-9-3: Applications in Transcription, Education and Learning I

On-Site Oral R110-111
Thu-O-OS-9-4: Spoken dialogue systems

On-Site Oral R113-115
Thu-SS-OS-9-5: The VoiceMOS Challenge

On-Site SS R116-118
Thu-P-OS-9-1: Speech Synthesis: Speaking Style, Emotion and Accents I

On-Site Poster Premier Ballroom
Thu-P-OS-9-2: Speech segmentation I

On-Site Poster Premier Ballroom
Thu-P-VR-9-3: Human speech & signal processing

Virtual Poster
Thu-P-VR-9-4: Speech Emotion Recognition II

Virtual Poster
Thu-P-VR-9-5: Speaker Recognition and Anti-Spoofing

Virtual Poster
Thu-P-VR-9-6: Miscellaneous topics in speech, voice and hearing disorders

Virtual Poster
Thu-SS-VR-9-7: Low-Resource ASR Development II

Virtual SS

Technical Program

September 22th, Thursday

Thu, 22 Sep, 13:30 - 15:30(KST)

Thu-O-OS-10-1: Voice Conversion and Adaptation I

On-Site Oral R104-106
Thu-O-OS-10-2: Search/Decoding algorithms for ASR

On-Site Oral R107-109
Thu-O-OS-10-3: Emotional speech production and perception

On-Site Oral R110-111
Thu-O-OS-10-4: Speech analysis

On-Site Oral R113-115
Thu-SS-OS-10-5: Trustworthy Speech Processing

On-Site SS R116-118
Thu-P-OS-10-1: Speaker Recognition and Diarization

On-Site Poster Premier Ballroom
Thu-P-OS-10-2: Self-supervised, Semi-Supervised, Adaptation and Data Augmentation for ASR II

On-Site Poster Premier Ballroom
Thu-P-OS-10-3: Spoken Language Processing I

On-Site Poster Premier Ballroom
Thu-ST-OS-10-4: Show and Tell IV

On-Site Show&Tell Premier Ballroom
Thu-P-VR-10-5: Phonetics II

Virtual Poster
Thu-P-VR-10-6: Source separation III

Virtual Poster
Thu-P-VR-10-7: Speech enhancement and intelligibility

Virtual Poster
Thu-P-VR-10-8: Speech Synthesis: Speaking Style, Emotion and Accents II

Virtual Poster
Thu-ST-VR-10-9: Show and Tell IV

Virtual Show&Tell

Sponsor

Founding

Platinum

Diamond

Gold

Silver

Bronze

Supported
by

Top