Journal article Open Access

Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech Synthesis

Al-Radhi, Mohammed Salah; Csapó, Tamás Gábor; Németh, Géza


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/5c930870-4d63-493c-a2bb-46465df9c9ec/applsci-09-02460.pdf"
      }, 
      "checksum": "md5:8e2b0b3591bc7c49771d98cc56f7acfd", 
      "bucket": "5c930870-4d63-493c-a2bb-46465df9c9ec", 
      "key": "applsci-09-02460.pdf", 
      "type": "pdf", 
      "size": 3595588
    }
  ], 
  "owners": [
    267448
  ], 
  "doi": "10.3390/app9122460", 
  "stats": {
    "version_unique_downloads": 15.0, 
    "unique_views": 15.0, 
    "views": 19.0, 
    "version_views": 19.0, 
    "unique_downloads": 15.0, 
    "version_unique_views": 15.0, 
    "volume": 64720584.0, 
    "version_downloads": 18.0, 
    "downloads": 18.0, 
    "version_volume": 64720584.0
  }, 
  "links": {
    "doi": "https://doi.org/10.3390/app9122460", 
    "latest_html": "https://zenodo.org/record/5729320", 
    "bucket": "https://zenodo.org/api/files/5c930870-4d63-493c-a2bb-46465df9c9ec", 
    "badge": "https://zenodo.org/badge/doi/10.3390/app9122460.svg", 
    "html": "https://zenodo.org/record/5729320", 
    "latest": "https://zenodo.org/api/records/5729320"
  }, 
  "created": "2021-11-26T11:26:36.331168+00:00", 
  "updated": "2021-11-26T17:42:27.442238+00:00", 
  "conceptrecid": "5729319", 
  "revision": 4, 
  "id": 5729320, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.3390/app9122460", 
    "version": "1", 
    "language": "eng", 
    "title": "Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech Synthesis", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.3390/app9122460", 
        "relation": "isCitedBy"
      }
    ], 
    "notes": "1", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "5729319"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "5729320"
          }
        }
      ]
    }, 
    "communities": [
      {
        "id": "ai4eu"
      }
    ], 
    "grants": [
      {
        "code": "825619", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::825619"
        }, 
        "title": "A European AI On Demand Platform and Ecosystem", 
        "acronym": "AI4EU", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "keywords": [
      "continuous F0", 
      "speech synthesis", 
      "time-warping"
    ], 
    "publication_date": "2019-06-16", 
    "creators": [
      {
        "orcid": "0000-0003-3094-6916", 
        "affiliation": "Budapest University of Technology and Economics", 
        "name": "Al-Radhi, Mohammed Salah"
      }, 
      {
        "orcid": "0000-0003-4375-7524", 
        "affiliation": "Budapest University of Technology and Economics", 
        "name": "Csap\u00f3, Tam\u00e1s G\u00e1bor"
      }, 
      {
        "orcid": "0000-0002-2311-4858", 
        "affiliation": "Budapest University of Technology and Economics", 
        "name": "N\u00e9meth, G\u00e9za"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "subtype": "article", 
      "type": "publication", 
      "title": "Journal article"
    }, 
    "description": "<p>Recent studies in text-to-speech synthesis have shown the benefit of using a continuous pitch estimate; one that interpolates fundamental frequency (F0) even when voicing is not present. However, continuous F0 is still sensitive to additive noise in speech signals and suffers from short-term errors (when it changes rather quickly over time). To alleviate these issues, three adaptive techniques have been developed in this article for achieving a robust and accurate F0: (1) we weight the pitch estimates with state noise covariance using adaptive Kalman-filter framework, (2) we iteratively apply a time axis warping on the input frame signal, (3) we optimize all F0 candidates using an instantaneous-frequency-based approach. Additionally, the second goal of this study is to introduce an extension of a novel continuous-based speech synthesis system (i.e., in which all parameters are continuous). We propose adding a new excitation parameter named Harmonic-to-Noise Ratio (HNR) to the voiced and unvoiced components to indicate the degree of voicing in the excitation and to reduce the influence of buzziness caused by the vocoder. Results based on objective and perceptual tests demonstrate that the voice built with the proposed framework gives state-of-the-art speech synthesis performance while outperforming the previous baseline.&nbsp;</p>"
  }
}
19
18
views
downloads
Views 19
Downloads 18
Data volume 64.7 MB
Unique views 15
Unique downloads 15

Share

Cite as