Speech Synthesis TRIZ Cases
- Text-Conditioned Speech Inpainting for Gaps Over 250 ms
A machine-learned audio inpainting model uses text transcripts to generate replacement speech content.
- Controllable Diffusion Speech Model Prosody Conversion
A diffusion-based speech generative model converts source audio to target voice using independent prosody embeddings.
- Neural Network Multi-Speaker Speech Synthesis via Adversarial Vector Prediction
A neural network synthesizes new speaker voices by predicting vectors from pre-trained models using adversarial training.
- Speech Synthesis Cadence Prediction Missing Parts
Predicting message template cadence allows selecting matching voice units and synthesizing missing parts, resolving discontinuous pitch at data boundaries.
- Text-to-Speech Normalization for Peculiar Expression Mood Reproduction
A text-to-speech normalizer converts peculiar expressions into standard forms to enable accurate speech synthesis.
- Speech Synthesis Dataset Fusion for Multi-Speaker Emotion
Fusing language speaker and emotion data within single utterances builds training datasets for speech synthesis models.
- Voice Synthesis Acoustic Watermarking for Device Identification
Audio synthesizer generates personalized voice output streams using extracted user characteristics and applies acoustic watermarks to identify machine-made audio.
- Multi-lingual Text-to-Speech Synthesizer with Inter-Lingual Tone
A multi-lingual speech synthesizer assembles phoneme sequences from separate language databases to generate natural-sounding voice messages.
- Foreign Language Pronunciation Correction via Waveform Matching
A foreign language learning apparatus uses text-to-speech waveforms to evaluate user voice input accuracy.
- Neural Network Speech Synthesis Acoustic Feature Matching
A speech synthesis system uses a neural network to determine target acoustic features from linguistic inputs for sample selection.
- Synthetic Voice Customization via Vocal Sample Analysis
A text-to-speech system creates a synthetic voice by measuring frequency, timbre, and rhythm from a recorded vocal sample.
- Text-to-Speech Emotional Content via Neutral Model Adjustments
A text-to-speech system applies emotion-specific adjustments to a neutral acoustic trajectory for expressive output.
- Syllable-Centered Polynomial Pitch Contour Generation
Polynomial expansion coefficients model pitch near syllable centers to resolve discontinuities in unvoiced segments and silence.
- Emotion-Targeted Speech Synthesis via Candidate Selection
A speech synthesis system generates diverse audio candidates for semantic content and selects the optimal segment to match a predetermined emotion type.
- Voice Differentiation via Perceptual Distance
Modifying pitch and formant parameters differentiates similar voices without requiring multiple audio channels.
- Empathetic Text-to-Speech Processing via Context-Aware Acoustic Code Generation
A machine learning model assigns sentence IDs to text segments, enabling context-aware generation of acoustic codes for natural speech rhythm and tone.
- Hybrid Speech Synthesis Using Phone-and-Transition Units
A hybrid speech synthesis system combines rule-based and concatenative methods using phone-and-transition units for natural voice output.
- Artificial Speech Generation with Emotional Indicators
A device extracts speech emotional indicators and timing data to generate artificial speech.
- Voice Prompt Caching Reduces Power and Network Usage
Electronic devices cache synthesized speech data locally to reuse prompts without repeated server requests.
- Distributed Voice Data Collection System for TTS Phoneme Coverage
A distributed voice data collection system gathers speech samples from multiple donors to build personalized text-to-speech models.