File: speech_recognition_recognizer_client_impl.h

package info (click to toggle)
chromium 139.0.7258.127-1
  • links: PTS, VCS
  • area: main
  • in suites:
  • size: 6,122,068 kB
  • sloc: cpp: 35,100,771; ansic: 7,163,530; javascript: 4,103,002; python: 1,436,920; asm: 946,517; xml: 746,709; pascal: 187,653; perl: 88,691; sh: 88,436; objc: 79,953; sql: 51,488; cs: 44,583; fortran: 24,137; makefile: 22,147; tcl: 15,277; php: 13,980; yacc: 8,984; ruby: 7,485; awk: 3,720; lisp: 3,096; lex: 1,327; ada: 727; jsp: 228; sed: 36
file content (108 lines) | stat: -rw-r--r-- 4,283 bytes parent folder | download | duplicates (6)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
// Copyright 2021 The Chromium Authors
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.

#ifndef CHROME_BROWSER_SPEECH_SPEECH_RECOGNITION_RECOGNIZER_CLIENT_IMPL_H_
#define CHROME_BROWSER_SPEECH_SPEECH_RECOGNITION_RECOGNIZER_CLIENT_IMPL_H_

#include <memory>
#include <string>

#include "ash/public/cpp/projector/speech_recognition_availability.h"
#include "base/memory/weak_ptr.h"
#include "chrome/browser/speech/speech_recognizer.h"
#include "chrome/browser/speech/speech_recognizer_delegate.h"
#include "media/audio/audio_system.h"
#include "media/mojo/mojom/speech_recognition_service.mojom.h"
#include "mojo/public/cpp/bindings/receiver.h"
#include "mojo/public/cpp/bindings/remote.h"

class Profile;
class SpeechRecognizerDelegate;

namespace media {
class AudioSystem;
}  // namespace media

// SpeechRecognitionRecognizerClientImpl is a wrapper around the on-device
// speech recognition engine that simplifies its use from the browser process.
// This client class is only used on ash chrome browser.
class SpeechRecognitionRecognizerClientImpl
    : public SpeechRecognizer,
      public media::mojom::SpeechRecognitionRecognizerClient {
 public:
  // Returns the availability of on-device speech recognition for the given
  // language (BCP-47 format, e.g. "en-US").
  static ash::OnDeviceRecognitionAvailability
  GetOnDeviceSpeechRecognitionAvailability(const std::string& language);

  // Returns the availability of server-based speech recognition for the given
  // language.
  static ash::ServerBasedRecognitionAvailability
  GetServerBasedRecognitionAvailability(const std::string& language);

  SpeechRecognitionRecognizerClientImpl(
      const base::WeakPtr<SpeechRecognizerDelegate>& delegate,
      Profile* profile,
      const std::string& device_id,
      media::mojom::SpeechRecognitionOptionsPtr options);
  ~SpeechRecognitionRecognizerClientImpl() override;
  SpeechRecognitionRecognizerClientImpl(
      const SpeechRecognitionRecognizerClientImpl&) = delete;
  SpeechRecognitionRecognizerClientImpl& operator=(
      const SpeechRecognitionRecognizerClientImpl&) = delete;

  // SpeechRecognizer:
  // Start and Stop must be called on the UI thread.
  void Start() override;
  void Stop() override;

  // media::mojom::SpeechRecognitionRecognizerClient:
  void OnSpeechRecognitionRecognitionEvent(
      const media::SpeechRecognitionResult& result,
      OnSpeechRecognitionRecognitionEventCallback reply) override;
  void OnSpeechRecognitionError() override;
  void OnLanguageIdentificationEvent(
      media::mojom::LanguageIdentificationEventPtr event) override;
  void OnSpeechRecognitionStopped() override;

  void set_audio_system_for_testing(
      std::unique_ptr<media::AudioSystem> audio_system) {
    audio_system_ = std::move(audio_system);
  }

 private:
  void OnRecognizerBound(bool success);
  void OnRecognizerDisconnected();
  void StartFetchingOnInputDeviceInfo(
      const std::optional<media::AudioParameters>& params);

  // Helper function to send the delegate updates to SpeechRecognizerStatus
  // only when the status has changed.
  void UpdateStatus(SpeechRecognizerStatus state);

  SpeechRecognizerStatus state_{SpeechRecognizerStatus::SPEECH_RECOGNIZER_OFF};
  std::string device_id_;
  bool is_multichannel_supported_{false};
  std::string language_;

  // Whether we are waiting for the AudioParameters callback to return. Used
  // to ensure Start doesn't keep starting if Stop or Error were called
  // in between requesting the callback and it running.
  bool waiting_for_params_{false};

  // Tests may use the audio system setter above after constructing an
  // SpeechRecognitionRecognizerClientImpl to override default behavior.
  std::unique_ptr<media::AudioSystem> audio_system_;

  mojo::Remote<media::mojom::AudioSourceSpeechRecognitionContext>
      audio_source_speech_recognition_context_;
  mojo::Remote<media::mojom::AudioSourceFetcher> audio_source_fetcher_;
  mojo::Receiver<media::mojom::SpeechRecognitionRecognizerClient>
      speech_recognition_client_receiver_{this};

  base::WeakPtrFactory<SpeechRecognitionRecognizerClientImpl> weak_factory_{
      this};
};

#endif  // CHROME_BROWSER_SPEECH_SPEECH_RECOGNITION_RECOGNIZER_CLIENT_IMPL_H_