Source: Interspeech 2024 ; 25th Interspeech Conference (Interspeech 2024) ; https://hal.science/hal-04683362 ; 25th Interspeech Conference (Interspeech 2024), Sep 2024, Kos,

تفاصيل العنوان

اقرأ أكثر حفظ في قائمتي

Conference

TalTech-IRIT-LIS Speaker and Language Diarization Systems for DISPLACE 2024

Authors : Kalda, Joonas; Alumae, Tanel; Lebourdais, Martin ...

Subjects: speech perception; intelligibility prediction; WhisperKos; Greece

Source: Interspeech 2024 ; 25th Interspeech Conference (Interspeech 2024) ; https://hal.science/hal-04683362 ; 25th Interspeech Conference (Interspeech 2024), Sep 2024, Kos,

تفاصيل العنوان

اقرأ أكثر حفظ في قائمتي

Conference

Zero-Shot End-To-End Spoken Question Answering In Medical Domain

Authors : Labrak, Yanis; Moumen, Adel; Dufour, Richard ...

Subjects: spoken question answering; large language model; medicalKos Island; Greece

Source: Interspeech 2024 ; https://hal.science/hal-04684874 ; Interspeech 2024, Sep 2024, Kos Island, Greece

تفاصيل العنوان

اقرأ أكثر حفظ في قائمتي

Conference

1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis

Authors : Ogun, Sewade; Owodunni, Abraham T.; Olatunji, Tobi ...

Subjects: text-to-speech; African-accented TTS; accented speechKos Island; Greece

Source: Interspeech 2024 ; https://hal.science/hal-04663033 ; Interspeech 2024, Sep 2024, Kos Island, Greece

تفاصيل العنوان

اقرأ أكثر حفظ في قائمتي

Conference

Perception of changes in source orientation-dependent reverberation for a visible virtual vocal source ; Perception des changements de réverbération en fonction de l'orientation de la source pour une source vocale virtuelle visible

Authors : Abehsera-Morell, Pablo; Poirier-Quinot, David; Katz, Brian, F. G. ...

Subjects: Acoustics; Directivity; Virtual realitySpainMadrid, Spain

Source: 156th Audio Engineering Society Conventionhttps://hal.science/hal-04606973156th Audio Engineering Society Convention, Audio Engineering Society, Jun 2024,

تفاصيل العنوان

اقرأ أكثر حفظ في قائمتي

Conference

Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS

Authors : Ogun, Sewade; Colotte, Vincent; Vincent, Emmanuel ...

Subjects: text-to-speech; pitch prediction; generative modelsDublin; Ireland

Source: InterSpeech 2023 ; https://hal.univ-lorraine.fr/hal-04108825 ; InterSpeech 2023, Aug 2023, Dublin, Ireland

تفاصيل العنوان

اقرأ أكثر حفظ في قائمتي

Conference

SuperOM: a SuperCollider class to generate music scores in OpenMusic

Authors : Panariello, Claudio; Frid, Emma;

Subjects: SuperCollider; OpenMusic; Computer assisted compositionBoston; United StatesBoston, United States

Source: Proceedings of the eighth international conference on technologies for music notation & representation ; International Conference on Technologies for Music Notation and Representation (TENOR) ;

تفاصيل العنوان

اقرأ أكثر حفظ في قائمتي

Conference

Transfer Learning and Bias Correction with Pre-trained Audio Embeddings

Authors : Wang, Changhong; Richard, Gaël; Mcfee, Brian ...

Subjects: Pre-trained audio embeddings; Bias correction; Transfer learningMilan; Italy

Source: Proceedings of the International Society for Music Information Retrieval Conference (ISMIR) ; The 24th conference of the International Society for Music Information Retrieval (ISMIR) ;

تفاصيل العنوان

اقرأ أكثر حفظ في قائمتي

نتائج البحث

فلترة النتائج

Zero-Shot End-To-End Spoken Question Answering In Medical Domain

Zero-Shot End-To-End Spoken Question Answering In Medical Domain

TalTech-IRIT-LIS Speaker and Language Diarization Systems for DISPLACE 2024

TalTech-IRIT-LIS Speaker and Language Diarization Systems for DISPLACE 2024

Zero-Shot End-To-End Spoken Question Answering In Medical Domain

1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis

Perception of changes in source orientation-dependent reverberation for a visible virtual vocal source ; Perception des changements de réverbération en fonction de l'orientation de la source pour une source vocale virtuelle visible

Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS

SuperOM: a SuperCollider class to generate music scores in OpenMusic

Transfer Learning and Bias Correction with Pre-trained Audio Embeddings

اتصل بنا

اتبع