A method for fundamental frequency estimation and voicing decision: Application to infant utterances recorded in real acoustical environments

By Tomohiro Nakatani, S. Amano, Toshio Irino, K. Ishizuka, T. Kondo. 2008

75 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations (2021, background): “Next, to evaluate the presence of F0 in the discrete units, we flattened the F0 units before synthesizing the signal and calculated VDE and FFE with respect to the original F0 values.”
Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron (2018, background): “The GPE measures the percentage of voiced frames that deviate in pitch by more than 20% compared to the reference.”
Text-Free Prosody-Aware Generative Spoken Language Modeling (2021, background): “Similarly to (Polyak et al., 2020) we report voice decision error (VDE) (Nakatani et al., 2008), which measures the portion of frames with voicing decision error and F0 Frame Error”
InstructTTS: Modelling Expressive TTS in Discrete Latent Space With Natural Language Style Prompt (2023, methodology): “For prosody similarity, we use three pitch-related metrics: Gross Pitch Error (GPE), Voicing Decision Error (VDE) [69] and F0 Frame Error (FFE) [70].”
In Other News: a Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data (2019, background): “Gross pitch error (GPE) (Nakatani et al., 2008) is measured as percentage of voiced frames whose relative lf0 error is more than 20%.”
Expressive Neural Voice Cloning (2021, methodology): “We use the following error metrics: Gross Pitch Error (GPE) [17], Voicing Decision Error (VDE) [17] and F0 Frame Error (FFE) [3].”
Reducing F0 Frame Error of F0 tracking algorithms under noisy conditions with an unvoiced/voiced classification frontend (2009, background): “The first is Voicing Decision Error (VDE) [3]:”
Unsupervised Speech Decomposition via Triple Information Bottleneck (2020, methodology): “SPEECHFLOW achieves a GPE of 1.04%, a VDE of 8.14%, and an FFE of 8.86%.”
Mellotron: Multispeaker Expressive Voice Synthesis by Conditioning on Rhythm, Pitch and Global Style Tokens (2019, unknown): “In this section we provide quantitative results that compare Gross Pitch Error (GPE) [20], Voicing Decision Error (VDE) [20] and F0 Frame Error (FFE) [21] between Mellotron and E2E-Prosody [1].”
Hierarchical Transfer Learning for Multilingual, Multi-Speaker, and Style Transfer DNN-Based TTS on Low-Resource Languages (2020, methodology): “Whereas the objective evaluations use four metrics as in [23]: mel-cepstral distortion (MCD K ) [59], gross pitch error (GPE) [60], voicing decision error (VDE) [60], and F0 frame error (FFE) [61].”
An Overview of Voice Conversion and Its Challenges: From Statistical Modeling to Deep Learning (2020, background): “We note that GPE reports the percentage of voiced frames whose pitch values are more than 20% different from the reference, while FFE reports the percentage of frames that either contain a 20% pitch error or a voicing decision error [263].”
Analysis and Assessment of Controllability of an Expressive Deep Learning-based TTS system (2021, unknown): “• VDE [26]: VDE = ∑ T−1 t=0 1[vt 6=v ′ t ] T • F0 MSE measuring a distance between F0 contours of prediction and ground truth: F0_MSE = 1 T ∑ T−1 t=0 (F0t − F′ 0t) 2 • lF0 MSE, similar to previous one in logarithmic scale: lF0_MSE = 1 T ∑ T−1 t=0 (log F0t − log F′ 0t) 2”
Towards Transfer Learning for End-to-End Speech Synthesis from Deep Pre-Trained Language Models (2019, background): “Gross Pitch Error (GPE) [24]: , where p t and ˆ p t are the pitch signals from the reference and generated audio, v t and ˆ v t are the voicing decisions from the reference and generated audio, and 1 denotes the indicator function.”