Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310273245> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4310273245 abstract "Spontaneous speech has many affective and pragmatic functions that are interesting and challenging to model in TTS (text-to-speech). However, the presence of reduced articulation, fillers, repetitions, and other disfluencies mean that text and acoustics are less well aligned than in read speech. This is problematic for attention-based TTS. We propose a TTS architecture that is particularly suited for rapidly learning to speak from irregular and small datasets while also reproducing the diversity of expressive phenomena present in spontaneous speech. Specifically, we modify an existing neural HMM-based TTS system, which is capable of stable, monotonic alignments for spontaneous speech, and add utterance-level prosody control, so that the system can represent the wide range of natural variability in a spontaneous speech corpus. We objectively evaluate control accuracy and perform a subjective listening test to compare to a system without prosody control. To exemplify the power of combining mid-level prosody control and ecologically valid data for reproducing intricate spontaneous speech phenomena, we evaluate the system's capability of synthesizing two types of creaky phonation. Audio samples are available at https://hfkml.github.io/pc_nhmm_tts/" @default.
- W4310273245 created "2022-11-30" @default.
- W4310273245 creator A5015417808 @default.
- W4310273245 creator A5055420969 @default.
- W4310273245 creator A5063795282 @default.
- W4310273245 creator A5090260243 @default.
- W4310273245 creator A5091432739 @default.
- W4310273245 date "2022-11-24" @default.
- W4310273245 modified "2023-10-02" @default.
- W4310273245 title "Prosody-controllable spontaneous TTS with neural HMMs" @default.
- W4310273245 doi "https://doi.org/10.48550/arxiv.2211.13533" @default.
- W4310273245 hasPublicationYear "2022" @default.
- W4310273245 type Work @default.
- W4310273245 citedByCount "0" @default.
- W4310273245 crossrefType "posted-content" @default.
- W4310273245 hasAuthorship W4310273245A5015417808 @default.
- W4310273245 hasAuthorship W4310273245A5055420969 @default.
- W4310273245 hasAuthorship W4310273245A5063795282 @default.
- W4310273245 hasAuthorship W4310273245A5090260243 @default.
- W4310273245 hasAuthorship W4310273245A5091432739 @default.
- W4310273245 hasBestOaLocation W43102732451 @default.
- W4310273245 hasConcept C138885662 @default.
- W4310273245 hasConcept C14999030 @default.
- W4310273245 hasConcept C154945302 @default.
- W4310273245 hasConcept C15744967 @default.
- W4310273245 hasConcept C173988693 @default.
- W4310273245 hasConcept C177291462 @default.
- W4310273245 hasConcept C17744445 @default.
- W4310273245 hasConcept C199539241 @default.
- W4310273245 hasConcept C204321447 @default.
- W4310273245 hasConcept C2775852435 @default.
- W4310273245 hasConcept C2779337067 @default.
- W4310273245 hasConcept C28490314 @default.
- W4310273245 hasConcept C41008148 @default.
- W4310273245 hasConcept C41895202 @default.
- W4310273245 hasConcept C46312422 @default.
- W4310273245 hasConcept C542774811 @default.
- W4310273245 hasConcept C94625758 @default.
- W4310273245 hasConceptScore W4310273245C138885662 @default.
- W4310273245 hasConceptScore W4310273245C14999030 @default.
- W4310273245 hasConceptScore W4310273245C154945302 @default.
- W4310273245 hasConceptScore W4310273245C15744967 @default.
- W4310273245 hasConceptScore W4310273245C173988693 @default.
- W4310273245 hasConceptScore W4310273245C177291462 @default.
- W4310273245 hasConceptScore W4310273245C17744445 @default.
- W4310273245 hasConceptScore W4310273245C199539241 @default.
- W4310273245 hasConceptScore W4310273245C204321447 @default.
- W4310273245 hasConceptScore W4310273245C2775852435 @default.
- W4310273245 hasConceptScore W4310273245C2779337067 @default.
- W4310273245 hasConceptScore W4310273245C28490314 @default.
- W4310273245 hasConceptScore W4310273245C41008148 @default.
- W4310273245 hasConceptScore W4310273245C41895202 @default.
- W4310273245 hasConceptScore W4310273245C46312422 @default.
- W4310273245 hasConceptScore W4310273245C542774811 @default.
- W4310273245 hasConceptScore W4310273245C94625758 @default.
- W4310273245 hasLocation W43102732451 @default.
- W4310273245 hasOpenAccess W4310273245 @default.
- W4310273245 hasPrimaryLocation W43102732451 @default.
- W4310273245 hasRelatedWork W1491396361 @default.
- W4310273245 hasRelatedWork W1742610407 @default.
- W4310273245 hasRelatedWork W1834107546 @default.
- W4310273245 hasRelatedWork W1866214668 @default.
- W4310273245 hasRelatedWork W1964529244 @default.
- W4310273245 hasRelatedWork W1967273212 @default.
- W4310273245 hasRelatedWork W2295316334 @default.
- W4310273245 hasRelatedWork W28791135 @default.
- W4310273245 hasRelatedWork W3140955690 @default.
- W4310273245 hasRelatedWork W4293523272 @default.
- W4310273245 isParatext "false" @default.
- W4310273245 isRetracted "false" @default.
- W4310273245 workType "article" @default.