Можно ли получить синхронизацию слов из текста в речь в Watson Java API?

Question

Мой учитель дал Java пример того, как генерировать речь из текста и сохранять в файл WAV. Он попросил нас изменить его, чтобы сохранить синхронизацию слов на диске. Я не вижу никаких вариантов сделать это в SynthesizeOptions (http://watson-developer-cloud.github.io/java-sdk/docs/java-sdk-7.2.0/com/ibm/watson/text_to_speech/v1/model/SynthesizeOptions.Builder.html), хотя API говорит, что это возможно: https://cloud.ibm.com/docs/services/text-to-speech?topic=text-to-speech-timing#timingRequest

Authenticator authenticator = new IamAuthenticator("api_key");
        TextToSpeech textToSpeech = new TextToSpeech(authenticator);


        try {

            SynthesizeOptions synthesizeOptions = new SynthesizeOptions.Builder()
                    .text(text)
                    .accept("audio/wav")
                    .voice("pt-BR_IsabelaV3Voice")
                    .timings(words)
                    .build();

            // a callback is defined to handle certain events, like an audio transmission or a timing marker
            // in this case, we'll build up a byte array of all the received bytes to build the resulting file
            final ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();

            textToSpeech.synthesizeUsingWebSocket(synthesizeOptions, new BaseSynthesizeCallback() {
                @Override
                public void onAudioStream(byte[] bytes) {
                    // append to our byte array
                    try {
                        byteArrayOutputStream.write(bytes);
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                }

            });


            // quick way to wait for synthesis to complete, since synthesizeUsingWebSocket() runs asynchronously
            try {
                Thread.sleep(5000);
            } catch (InterruptedException e) {
                e.printStackTrace();
            }

            // create file with audio data
            String filename = id + ".wav";
            OutputStream fileOutputStream = new FileOutputStream(filename);
            byteArrayOutputStream.writeTo(fileOutputStream);

            // clean up
            byteArrayOutputStream.close();
            fileOutputStream.close();


        } catch (IOException e) {
            e.printStackTrace();
        }

Answer 1

package com.watsontest;

import java.io.*;
//import java.io.IOExceintellintellij ideaption;
import java.util.ArrayList;

import com.google.gson.Gson;
import com.ibm.cloud.sdk.core.http.HttpMediaType;
import com.ibm.cloud.sdk.core.security.Authenticator;
import com.ibm.cloud.sdk.core.security.IamAuthenticator;
import com.ibm.watson.speech_to_text.v1.SpeechToText;
import com.ibm.watson.speech_to_text.v1.model.RecognizeOptions;
import com.ibm.watson.speech_to_text.v1.model.SpeechRecognitionResults;
import com.ibm.watson.text_to_speech.v1.TextToSpeech;
import com.ibm.watson.text_to_speech.v1.model.SynthesizeOptions;
import com.ibm.watson.text_to_speech.v1.model.Timings;
import com.ibm.watson.text_to_speech.v1.websocket.BaseSynthesizeCallback;


public class Main {
    public void geraVoz(String id, String text, ArrayList<String> words){
        Authenticator authenticator = new IamAuthenticator("API_KEY_HERE");
        TextToSpeech textToSpeech = new TextToSpeech(authenticator);
        ArrayList arrayList = new ArrayList<String>();
        arrayList.add("words");
        ArrayList timingsArrayList = new ArrayList<Timings>();
        try {
            SynthesizeOptions synthesizeOptions = new SynthesizeOptions.Builder()
                    .text(text)
                    .accept("audio/wav")
                    .voice("pt-BR_IsabelaV3Voice")
                    .timings(arrayList)
                    .build();

            // a callback is defined to handle certain events, like an audio transmission or a timing marker
            // in this case, we'll build up a byte array of all the received bytes to build the resulting file
            final ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();

            textToSpeech.synthesizeUsingWebSocket(synthesizeOptions, new BaseSynthesizeCallback() {
                @Override
                public void onAudioStream(byte[] bytes) {
                    // append to our byte array
                    try {
                        byteArrayOutputStream.write(bytes);
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                }
                @Override
                public void onTimings(Timings timings) {
                    timingsArrayList.add(timings);
                }
                @Override
                public void onDisconnected() {
                    System.out.println("disconnected!");
                    String json = new Gson().toJson(timingsArrayList);

                    try {
                        PrintWriter out = new PrintWriter("timings.json");
                        out.println(json);
                        out.close();
                    } catch (Exception e) {
                        System.out.println(e);
                    }
                }
            });

            // quick way to wait for synthesis to complete, since synthesizeUsingWebSocket() runs asynchronously
            try {
                Thread.sleep(5000);
            } catch (InterruptedException e) {
                e.printStackTrace();
            }

            // create file with audio data
            String filename = id + ".wav";
            OutputStream fileOutputStream = new FileOutputStream(filename);
            byteArrayOutputStream.writeTo(fileOutputStream);
            System.out.println(synthesizeOptions.getTimings());
            // clean up
            byteArrayOutputStream.close();
            fileOutputStream.close();
            System.out.println("recorded file");

        } catch (IOException e) {
            e.printStackTrace();
        }
    }


    public static void main(String[] args) {
        new Main().geraVoz("id1", "testando transcrição de voz. Olá isso é um teste", null);
    }
}

Answer 2

Вы должны думать из коробки. У вас есть аудиофайл, а синхронизация слов - это функция речевых и текстовых сервисов, а не текстовых речевых сервисов.